This commit is contained in:
Anna Nowak 2021-05-16 12:04:03 +02:00
parent 2da1e8b7d9
commit 3833bbc547
2 changed files with 319 additions and 456 deletions

View File

@ -66,13 +66,31 @@
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"C:\\Users\\domstr2\\l07\n" "C:\\Users\\Ania\\Desktop\\System_Dialogowy_Janet\\l07\n"
] ]
}, },
{ {
"name": "stderr", "name": "stderr",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"A subdirectory or file -p already exists.\n",
"Error occurred while processing: -p.\n",
"A subdirectory or file l07 already exists.\n",
"Error occurred while processing: l07.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"C:\\Users\\Ania\\Desktop\\System_Dialogowy_Janet\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"** Resuming transfer from byte position 8923190\n",
" % Total % Received % Xferd Average Speed Time Time Time Current\n", " % Total % Received % Xferd Average Speed Time Time Time Current\n",
" Dload Upload Total Spent Left Speed\n", " Dload Upload Total Spent Left Speed\n",
"\n", "\n",
@ -80,23 +98,7 @@
" 0 0 0 0 0 0 0 0 --:--:-- --:--:-- --:--:-- 0\n", " 0 0 0 0 0 0 0 0 --:--:-- --:--:-- --:--:-- 0\n",
"\n", "\n",
" 0 0 0 0 0 0 0 0 --:--:-- --:--:-- --:--:-- 0\n", " 0 0 0 0 0 0 0 0 --:--:-- --:--:-- --:--:-- 0\n",
" 1 8714k 1 95352 0 0 66216 0 0:02:14 0:00:01 0:02:13 93666\n", "100 49 100 49 0 0 56 0 --:--:-- --:--:-- --:--:-- 742\n"
"100 8714k 100 8714k 0 0 4211k 0 0:00:02 0:00:02 --:--:-- 5290k\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"C:\\Users\\domstr2\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"'unzip' is not recognized as an internal or external command,\n",
"operable program or batch file.\n"
] ]
} }
], ],
@ -116,14 +118,14 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 30, "execution_count": 2,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"Requirement already satisfied: conllu in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (4.4)\n" "Requirement already satisfied: conllu in c:\\programdata\\anaconda3\\lib\\site-packages (4.4)\n"
] ]
} }
], ],
@ -136,9 +138,9 @@
"def nolabel2o(line, i):\n", "def nolabel2o(line, i):\n",
" return 'O' if line[i] == 'NoLabel' else line[i]\n", " return 'O' if line[i] == 'NoLabel' else line[i]\n",
"\n", "\n",
"with open('l07/Janet_test.conllu', encoding='utf-8') as trainfile:\n", "with open('Janet_test.conllu', encoding='utf-8') as trainfile:\n",
" trainset = list(parse_incr(trainfile, fields=fields, field_parsers={'slot': nolabel2o}))\n", " trainset = list(parse_incr(trainfile, fields=fields, field_parsers={'slot': nolabel2o}))\n",
"with open('l07/Janet_test.conllu', encoding='utf-8') as testfile:\n", "with open('Janet_test.conllu', encoding='utf-8') as testfile:\n",
" testset = list(parse_incr(testfile, fields=fields, field_parsers={'slot': nolabel2o}))" " testset = list(parse_incr(testfile, fields=fields, field_parsers={'slot': nolabel2o}))"
] ]
}, },
@ -151,14 +153,14 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 31, "execution_count": 3,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"Requirement already satisfied: tabulate in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (0.8.9)" "Requirement already satisfied: tabulate in c:\\programdata\\anaconda3\\lib\\site-packages (0.8.9)\n"
] ]
}, },
{ {
@ -174,16 +176,9 @@
"'<table>\\n<tbody>\\n<tr><td style=\"text-align: right;\">1</td><td>hej</td><td>greeting</td><td>O</td></tr>\\n</tbody>\\n</table>'" "'<table>\\n<tbody>\\n<tr><td style=\"text-align: right;\">1</td><td>hej</td><td>greeting</td><td>O</td></tr>\\n</tbody>\\n</table>'"
] ]
}, },
"execution_count": 31, "execution_count": 3,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
} }
], ],
"source": [ "source": [
@ -192,76 +187,6 @@
"tabulate(trainset[0], tablefmt='html')" "tabulate(trainset[0], tablefmt='html')"
] ]
}, },
{
"cell_type": "code",
"execution_count": 32,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<table>\n",
"<tbody>\n",
"<tr><td style=\"text-align: right;\">1</td><td>chcialbym</td><td>prescription/collect</td><td>O</td></tr>\n",
"<tr><td style=\"text-align: right;\">2</td><td>odebrac </td><td>prescription/collect</td><td>O</td></tr>\n",
"<tr><td style=\"text-align: right;\">3</td><td>receptę </td><td>prescription/collect</td><td>O</td></tr>\n",
"</tbody>\n",
"</table>"
],
"text/plain": [
"'<table>\\n<tbody>\\n<tr><td style=\"text-align: right;\">1</td><td>chcialbym</td><td>prescription/collect</td><td>O</td></tr>\\n<tr><td style=\"text-align: right;\">2</td><td>odebrac </td><td>prescription/collect</td><td>O</td></tr>\\n<tr><td style=\"text-align: right;\">3</td><td>receptę </td><td>prescription/collect</td><td>O</td></tr>\\n</tbody>\\n</table>'"
]
},
"execution_count": 32,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tabulate(trainset[10], tablefmt='html')"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<table>\n",
"<tbody>\n",
"<tr><td style=\"text-align: right;\"> 1</td><td>dzień </td><td>appoinment/create_appointment</td><td>O </td></tr>\n",
"<tr><td style=\"text-align: right;\"> 2</td><td>dobry, </td><td>appoinment/create_appointment</td><td>O </td></tr>\n",
"<tr><td style=\"text-align: right;\"> 3</td><td>chciałbym </td><td>appoinment/create_appointment</td><td>O </td></tr>\n",
"<tr><td style=\"text-align: right;\"> 4</td><td>umówić </td><td>appoinment/create_appointment</td><td>O </td></tr>\n",
"<tr><td style=\"text-align: right;\"> 5</td><td>się </td><td>appoinment/create_appointment</td><td>O </td></tr>\n",
"<tr><td style=\"text-align: right;\"> 6</td><td>na </td><td>appoinment/create_appointment</td><td>O </td></tr>\n",
"<tr><td style=\"text-align: right;\"> 7</td><td>wizytę </td><td>appoinment/create_appointment</td><td>O </td></tr>\n",
"<tr><td style=\"text-align: right;\"> 8</td><td>do </td><td>appoinment/create_appointment</td><td>O </td></tr>\n",
"<tr><td style=\"text-align: right;\"> 9</td><td>lekarza </td><td>appoinment/create_appointment</td><td>B-appoinment/doctor</td></tr>\n",
"<tr><td style=\"text-align: right;\">10</td><td>rodzinnego. </td><td>appoinment/create_appointment</td><td>I-appoinment/doctor</td></tr>\n",
"<tr><td style=\"text-align: right;\">11</td><td>najlepiej </td><td>appoinment/create_appointment</td><td>O </td></tr>\n",
"<tr><td style=\"text-align: right;\">12</td><td>dzisiaj </td><td>appoinment/create_appointment</td><td>B-datetime </td></tr>\n",
"<tr><td style=\"text-align: right;\">13</td><td>w </td><td>appoinment/create_appointment</td><td>I-datetime </td></tr>\n",
"<tr><td style=\"text-align: right;\">14</td><td>godzinach </td><td>appoinment/create_appointment</td><td>I-datetime </td></tr>\n",
"<tr><td style=\"text-align: right;\">15</td><td>popołudniowych.</td><td>appoinment/create_appointment</td><td>I-datetime </td></tr>\n",
"</tbody>\n",
"</table>"
],
"text/plain": [
"'<table>\\n<tbody>\\n<tr><td style=\"text-align: right;\"> 1</td><td>dzień </td><td>appoinment/create_appointment</td><td>O </td></tr>\\n<tr><td style=\"text-align: right;\"> 2</td><td>dobry, </td><td>appoinment/create_appointment</td><td>O </td></tr>\\n<tr><td style=\"text-align: right;\"> 3</td><td>chciałbym </td><td>appoinment/create_appointment</td><td>O </td></tr>\\n<tr><td style=\"text-align: right;\"> 4</td><td>umówić </td><td>appoinment/create_appointment</td><td>O </td></tr>\\n<tr><td style=\"text-align: right;\"> 5</td><td>się </td><td>appoinment/create_appointment</td><td>O </td></tr>\\n<tr><td style=\"text-align: right;\"> 6</td><td>na </td><td>appoinment/create_appointment</td><td>O </td></tr>\\n<tr><td style=\"text-align: right;\"> 7</td><td>wizytę </td><td>appoinment/create_appointment</td><td>O </td></tr>\\n<tr><td style=\"text-align: right;\"> 8</td><td>do </td><td>appoinment/create_appointment</td><td>O </td></tr>\\n<tr><td style=\"text-align: right;\"> 9</td><td>lekarza </td><td>appoinment/create_appointment</td><td>B-appoinment/doctor</td></tr>\\n<tr><td style=\"text-align: right;\">10</td><td>rodzinnego. </td><td>appoinment/create_appointment</td><td>I-appoinment/doctor</td></tr>\\n<tr><td style=\"text-align: right;\">11</td><td>najlepiej </td><td>appoinment/create_appointment</td><td>O </td></tr>\\n<tr><td style=\"text-align: right;\">12</td><td>dzisiaj </td><td>appoinment/create_appointment</td><td>B-datetime </td></tr>\\n<tr><td style=\"text-align: right;\">13</td><td>w </td><td>appoinment/create_appointment</td><td>I-datetime </td></tr>\\n<tr><td style=\"text-align: right;\">14</td><td>godzinach </td><td>appoinment/create_appointment</td><td>I-datetime </td></tr>\\n<tr><td style=\"text-align: right;\">15</td><td>popołudniowych.</td><td>appoinment/create_appointment</td><td>I-datetime </td></tr>\\n</tbody>\\n</table>'"
]
},
"execution_count": 33,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tabulate(trainset[1], tablefmt='html')"
]
},
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": { "metadata": {
@ -271,33 +196,6 @@
"Na potrzeby prezentacji procesu uczenia w jupyterowym notatniku zawęzimy zbiór danych do początkowych przykładów." "Na potrzeby prezentacji procesu uczenia w jupyterowym notatniku zawęzimy zbiór danych do początkowych przykładów."
] ]
}, },
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"trainset = trainset[:100]\n",
"testset = testset[:100]"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"ąę\n"
]
}
],
"source": [
"print('ąę')"
]
},
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
@ -308,100 +206,91 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 14, "execution_count": 4,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"Requirement already satisfied: flair in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (0.8.0.post1)\n", "Requirement already satisfied: flair in c:\\programdata\\anaconda3\\lib\\site-packages (0.8.0.post1)\n",
"Requirement already satisfied: tqdm>=4.26.0 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from flair) (4.50.2)\n", "Requirement already satisfied: huggingface-hub in c:\\programdata\\anaconda3\\lib\\site-packages (from flair) (0.0.8)\n",
"Requirement already satisfied: matplotlib>=2.2.3 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from flair) (3.3.2)\n", "Requirement already satisfied: mpld3==0.3 in c:\\programdata\\anaconda3\\lib\\site-packages (from flair) (0.3)\n",
"Requirement already satisfied: hyperopt>=0.1.1 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from flair) (0.2.5)\n", "Requirement already satisfied: langdetect in c:\\programdata\\anaconda3\\lib\\site-packages (from flair) (1.0.9)\n",
"Requirement already satisfied: ftfy in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from flair) (6.0.1)\n", "Requirement already satisfied: hyperopt>=0.1.1 in c:\\programdata\\anaconda3\\lib\\site-packages (from flair) (0.2.5)\n",
"Requirement already satisfied: konoha<5.0.0,>=4.0.0 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from flair) (4.6.4)\n", "Requirement already satisfied: tabulate in c:\\programdata\\anaconda3\\lib\\site-packages (from flair) (0.8.9)\n",
"Requirement already satisfied: bpemb>=0.3.2 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from flair) (0.3.3)\n", "Requirement already satisfied: torch<=1.7.1,>=1.5.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from flair) (1.7.1)\n",
"Requirement already satisfied: janome in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from flair) (0.4.1)\n", "Requirement already satisfied: matplotlib>=2.2.3 in c:\\programdata\\anaconda3\\lib\\site-packages (from flair) (3.3.2)\n",
"Requirement already satisfied: scikit-learn>=0.21.3 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from flair) (0.23.2)\n", "Requirement already satisfied: sentencepiece==0.1.95 in c:\\programdata\\anaconda3\\lib\\site-packages (from flair) (0.1.95)\n",
"Requirement already satisfied: transformers>=4.0.0 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from flair) (4.5.1)\n", "Requirement already satisfied: numpy<1.20.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from flair) (1.19.2)\n",
"Requirement already satisfied: gdown==3.12.2 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from flair) (3.12.2)\n", "Requirement already satisfied: sqlitedict>=1.6.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from flair) (1.7.0)\n",
"Requirement already satisfied: tabulate in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from flair) (0.8.9)\n", "Requirement already satisfied: lxml in c:\\programdata\\anaconda3\\lib\\site-packages (from flair) (4.6.1)\n",
"Requirement already satisfied: langdetect in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from flair) (1.0.9)\n", "Requirement already satisfied: python-dateutil>=2.6.1 in c:\\programdata\\anaconda3\\lib\\site-packages (from flair) (2.8.1)\n",
"Requirement already satisfied: python-dateutil>=2.6.1 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from flair) (2.8.1)\n", "Requirement already satisfied: gensim<=3.8.3,>=3.4.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from flair) (3.8.3)\n",
"Requirement already satisfied: deprecated>=1.2.4 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from flair) (1.2.12)\n", "Requirement already satisfied: deprecated>=1.2.4 in c:\\programdata\\anaconda3\\lib\\site-packages (from flair) (1.2.12)\n",
"Requirement already satisfied: huggingface-hub in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from flair) (0.0.8)\n", "Requirement already satisfied: gdown==3.12.2 in c:\\programdata\\anaconda3\\lib\\site-packages (from flair) (3.12.2)\n",
"Requirement already satisfied: regex in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from flair) (2020.10.15)\n", "Requirement already satisfied: janome in c:\\programdata\\anaconda3\\lib\\site-packages (from flair) (0.4.1)\n",
"Requirement already satisfied: numpy<1.20.0 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from flair) (1.19.2)\n", "Requirement already satisfied: konoha<5.0.0,>=4.0.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from flair) (4.6.4)\n",
"Requirement already satisfied: gensim<=3.8.3,>=3.4.0 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from flair) (3.8.3)\n", "Requirement already satisfied: bpemb>=0.3.2 in c:\\programdata\\anaconda3\\lib\\site-packages (from flair) (0.3.3)\n",
"Requirement already satisfied: sqlitedict>=1.6.0 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from flair) (1.7.0)\n", "Requirement already satisfied: tqdm>=4.26.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from flair) (4.50.2)\n",
"Requirement already satisfied: lxml in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from flair) (4.6.1)\n", "Requirement already satisfied: segtok>=1.5.7 in c:\\programdata\\anaconda3\\lib\\site-packages (from flair) (1.5.10)\n",
"Requirement already satisfied: sentencepiece==0.1.95 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from flair) (0.1.95)\n", "Requirement already satisfied: transformers>=4.0.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from flair) (4.6.0)\n",
"Requirement already satisfied: segtok>=1.5.7 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from flair) (1.5.10)\n", "Requirement already satisfied: regex in c:\\programdata\\anaconda3\\lib\\site-packages (from flair) (2020.10.15)\n",
"Requirement already satisfied: torch<=1.7.1,>=1.5.0 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from flair) (1.7.1)\n", "Requirement already satisfied: scikit-learn>=0.21.3 in c:\\programdata\\anaconda3\\lib\\site-packages (from flair) (0.23.2)\n",
"Requirement already satisfied: mpld3==0.3 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from flair) (0.3)\n", "Requirement already satisfied: ftfy in c:\\programdata\\anaconda3\\lib\\site-packages (from flair) (6.0.1)\n",
"Requirement already satisfied: pillow>=6.2.0 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from matplotlib>=2.2.3->flair) (8.0.1)\n", "Requirement already satisfied: filelock in c:\\programdata\\anaconda3\\lib\\site-packages (from huggingface-hub->flair) (3.0.12)\n",
"Requirement already satisfied: pyparsing!=2.0.4,!=2.1.2,!=2.1.6,>=2.0.3 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from matplotlib>=2.2.3->flair) (2.4.7)\n", "Requirement already satisfied: requests in c:\\programdata\\anaconda3\\lib\\site-packages (from huggingface-hub->flair) (2.24.0)\n",
"Requirement already satisfied: cycler>=0.10 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from matplotlib>=2.2.3->flair) (0.10.0)\n", "Requirement already satisfied: six in c:\\programdata\\anaconda3\\lib\\site-packages (from langdetect->flair) (1.15.0)\n",
"Requirement already satisfied: certifi>=2020.06.20 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from matplotlib>=2.2.3->flair) (2020.6.20)\n", "Requirement already satisfied: future in c:\\programdata\\anaconda3\\lib\\site-packages (from hyperopt>=0.1.1->flair) (0.18.2)\n",
"Requirement already satisfied: kiwisolver>=1.0.1 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from matplotlib>=2.2.3->flair) (1.3.0)\n", "Requirement already satisfied: scipy in c:\\programdata\\anaconda3\\lib\\site-packages (from hyperopt>=0.1.1->flair) (1.5.2)\n",
"Requirement already satisfied: six in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from hyperopt>=0.1.1->flair) (1.15.0)\n", "Requirement already satisfied: cloudpickle in c:\\programdata\\anaconda3\\lib\\site-packages (from hyperopt>=0.1.1->flair) (1.6.0)\n",
"Requirement already satisfied: future in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from hyperopt>=0.1.1->flair) (0.18.2)\n", "Requirement already satisfied: networkx>=2.2 in c:\\programdata\\anaconda3\\lib\\site-packages (from hyperopt>=0.1.1->flair) (2.5)\n",
"Requirement already satisfied: scipy in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from hyperopt>=0.1.1->flair) (1.5.2)\n", "Requirement already satisfied: typing-extensions in c:\\programdata\\anaconda3\\lib\\site-packages (from torch<=1.7.1,>=1.5.0->flair) (3.7.4.3)\n",
"Requirement already satisfied: cloudpickle in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from hyperopt>=0.1.1->flair) (1.6.0)\n", "Requirement already satisfied: certifi>=2020.06.20 in c:\\programdata\\anaconda3\\lib\\site-packages (from matplotlib>=2.2.3->flair) (2020.6.20)\n",
"Requirement already satisfied: networkx>=2.2 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from hyperopt>=0.1.1->flair) (2.5)\n", "Requirement already satisfied: pyparsing!=2.0.4,!=2.1.2,!=2.1.6,>=2.0.3 in c:\\programdata\\anaconda3\\lib\\site-packages (from matplotlib>=2.2.3->flair) (2.4.7)\n",
"Requirement already satisfied: wcwidth in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from ftfy->flair) (0.2.5)\n", "Requirement already satisfied: pillow>=6.2.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from matplotlib>=2.2.3->flair) (8.0.1)\n",
"Requirement already satisfied: importlib-metadata<4.0.0,>=3.7.0 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from konoha<5.0.0,>=4.0.0->flair) (3.10.1)\n", "Requirement already satisfied: kiwisolver>=1.0.1 in c:\\programdata\\anaconda3\\lib\\site-packages (from matplotlib>=2.2.3->flair) (1.3.0)\n",
"Collecting requests<3.0.0,>=2.25.1\n", "Requirement already satisfied: cycler>=0.10 in c:\\programdata\\anaconda3\\lib\\site-packages (from matplotlib>=2.2.3->flair) (0.10.0)\n",
" Using cached requests-2.25.1-py2.py3-none-any.whl (61 kB)\n", "Requirement already satisfied: Cython==0.29.14 in c:\\programdata\\anaconda3\\lib\\site-packages (from gensim<=3.8.3,>=3.4.0->flair) (0.29.14)\n",
"Requirement already satisfied: overrides<4.0.0,>=3.0.0 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from konoha<5.0.0,>=4.0.0->flair) (3.1.0)\n", "Requirement already satisfied: smart-open>=1.8.1 in c:\\programdata\\anaconda3\\lib\\site-packages (from gensim<=3.8.3,>=3.4.0->flair) (5.0.0)\n",
"Requirement already satisfied: threadpoolctl>=2.0.0 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from scikit-learn>=0.21.3->flair) (2.1.0)\n", "Requirement already satisfied: wrapt<2,>=1.10 in c:\\users\\ania\\appdata\\roaming\\python\\python38\\site-packages (from deprecated>=1.2.4->flair) (1.12.1)\n",
"Requirement already satisfied: joblib>=0.11 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from scikit-learn>=0.21.3->flair) (0.17.0)\n", "Requirement already satisfied: importlib-metadata<4.0.0,>=3.7.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from konoha<5.0.0,>=4.0.0->flair) (3.10.1)\n",
"Requirement already satisfied: sacremoses in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from transformers>=4.0.0->flair) (0.0.45)\n", "Requirement already satisfied: overrides<4.0.0,>=3.0.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from konoha<5.0.0,>=4.0.0->flair) (3.1.0)\n",
"Requirement already satisfied: packaging in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from transformers>=4.0.0->flair) (20.4)\n", "Requirement already satisfied: packaging in c:\\programdata\\anaconda3\\lib\\site-packages (from transformers>=4.0.0->flair) (20.4)\n",
"Requirement already satisfied: filelock in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from transformers>=4.0.0->flair) (3.0.12)\n", "Requirement already satisfied: tokenizers<0.11,>=0.10.1 in c:\\programdata\\anaconda3\\lib\\site-packages (from transformers>=4.0.0->flair) (0.10.2)\n",
"Requirement already satisfied: tokenizers<0.11,>=0.10.1 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from transformers>=4.0.0->flair) (0.10.2)\n", "Requirement already satisfied: sacremoses in c:\\programdata\\anaconda3\\lib\\site-packages (from transformers>=4.0.0->flair) (0.0.45)\n",
"Requirement already satisfied: wrapt<2,>=1.10 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from deprecated>=1.2.4->flair) (1.12.1)\n", "Requirement already satisfied: joblib>=0.11 in c:\\programdata\\anaconda3\\lib\\site-packages (from scikit-learn>=0.21.3->flair) (0.17.0)\n",
"Requirement already satisfied: Cython==0.29.14 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from gensim<=3.8.3,>=3.4.0->flair) (0.29.14)\n", "Requirement already satisfied: threadpoolctl>=2.0.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from scikit-learn>=0.21.3->flair) (2.1.0)\n",
"Requirement already satisfied: smart-open>=1.8.1 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from gensim<=3.8.3,>=3.4.0->flair) (5.0.0)\n", "Requirement already satisfied: wcwidth in c:\\programdata\\anaconda3\\lib\\site-packages (from ftfy->flair) (0.2.5)\n",
"Requirement already satisfied: typing-extensions in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from torch<=1.7.1,>=1.5.0->flair) (3.7.4.3)\n", "Requirement already satisfied: idna<3,>=2.5 in c:\\programdata\\anaconda3\\lib\\site-packages (from requests->huggingface-hub->flair) (2.10)\n",
"Requirement already satisfied: decorator>=4.3.0 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from networkx>=2.2->hyperopt>=0.1.1->flair) (4.4.2)\n", "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in c:\\programdata\\anaconda3\\lib\\site-packages (from requests->huggingface-hub->flair) (1.25.11)\n",
"Requirement already satisfied: zipp>=0.5 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from importlib-metadata<4.0.0,>=3.7.0->konoha<5.0.0,>=4.0.0->flair) (3.4.0)\n", "Requirement already satisfied: chardet<4,>=3.0.2 in c:\\programdata\\anaconda3\\lib\\site-packages (from requests->huggingface-hub->flair) (3.0.4)\n",
"Requirement already satisfied: idna<3,>=2.5 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from requests<3.0.0,>=2.25.1->konoha<5.0.0,>=4.0.0->flair) (2.10)\n", "Requirement already satisfied: decorator>=4.3.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from networkx>=2.2->hyperopt>=0.1.1->flair) (4.4.2)\n",
"Requirement already satisfied: chardet<5,>=3.0.2 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from requests<3.0.0,>=2.25.1->konoha<5.0.0,>=4.0.0->flair) (3.0.4)\n", "Requirement already satisfied: zipp>=0.5 in c:\\programdata\\anaconda3\\lib\\site-packages (from importlib-metadata<4.0.0,>=3.7.0->konoha<5.0.0,>=4.0.0->flair) (3.4.0)\n",
"Requirement already satisfied: urllib3<1.27,>=1.21.1 in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from requests<3.0.0,>=2.25.1->konoha<5.0.0,>=4.0.0->flair) (1.25.11)\n", "Requirement already satisfied: click in c:\\programdata\\anaconda3\\lib\\site-packages (from sacremoses->transformers>=4.0.0->flair) (7.1.2)\n"
"Requirement already satisfied: click in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from sacremoses->transformers>=4.0.0->flair) (7.1.2)\n", ]
"Installing collected packages: requests\n", }
" Attempting uninstall: requests\n", ],
" Found existing installation: requests 2.24.0\n", "source": [
" Uninstalling requests-2.24.0:\n", "!pip3 install flair"
" Successfully uninstalled requests-2.24.0\n", ]
"Successfully installed requests-2.25.1\n" },
] {
}, "cell_type": "code",
{ "execution_count": 5,
"name": "stderr", "metadata": {},
"output_type": "stream", "outputs": [
"text": [ {
"ERROR: After October 2020 you may experience errors when installing or updating packages. This is because pip will change the way that it resolves dependency conflicts.\n", "name": "stdout",
"\n", "output_type": "stream",
"We recommend you use --use-feature=2020-resolver to test your packages with the new resolver before it becomes the default.\n", "text": [
"\n", "Requirement already satisfied: torch in c:\\programdata\\anaconda3\\lib\\site-packages (1.7.1)\n",
"conda 4.10.1 requires ruamel_yaml_conda>=0.11.14, which is not installed.\n" "Requirement already satisfied: typing-extensions in c:\\programdata\\anaconda3\\lib\\site-packages (from torch) (3.7.4.3)\n",
] "Requirement already satisfied: numpy in c:\\programdata\\anaconda3\\lib\\site-packages (from torch) (1.19.2)\n"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Requirement already satisfied: torch in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (1.7.1)\n",
"Requirement already satisfied: typing-extensions in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from torch) (3.7.4.3)\n",
"Requirement already satisfied: numpy in c:\\users\\domstr2\\anaconda3\\lib\\site-packages (from torch) (1.19.2)\n"
] ]
} }
], ],
"source": [ "source": [
"!pip3 install flair\n",
"from flair.data import Corpus, Sentence, Token\n", "from flair.data import Corpus, Sentence, Token\n",
"from flair.datasets import SentenceDataset\n", "from flair.datasets import SentenceDataset\n",
"from flair.embeddings import StackedEmbeddings\n", "from flair.embeddings import StackedEmbeddings\n",
@ -435,15 +324,15 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 34, "execution_count": 6,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"Corpus: 37 train + 4 dev + 41 test sentences\n", "Corpus: 36 train + 4 dev + 40 test sentences\n",
"Dictionary with 13 tags: <unk>, O, B-appoinment/doctor, I-appoinment/doctor, B-datetime, I-datetime, B-login/id, B-login/password, B-appointment/type, I-appointment/type, B-prescription/type, <START>, <STOP>\n" "Dictionary with 13 tags: <unk>, O, B-appoinment/doctor, I-appoinment/doctor, B-datetime, I-datetime, B-login/id, B-appointment/type, I-appointment/type, B-prescription/type, B-login/password, <START>, <STOP>\n"
] ]
} }
], ],
@ -481,132 +370,9 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 24, "execution_count": 7,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [],
{
"name": "stdout",
"output_type": "stream",
"text": [
"2021-05-12 17:01:27,807 https://flair.informatik.hu-berlin.de/resources/embeddings/token/pl-wiki-fasttext-300d-1M.vectors.npy not found in cache, downloading to C:\\Users\\domstr2\\AppData\\Local\\Temp\\tmpq9mlzfps\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████| 1199998928/1199998928 [00:52<00:00, 22832915.30B/s]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"2021-05-12 17:02:20,552 copying C:\\Users\\domstr2\\AppData\\Local\\Temp\\tmpq9mlzfps to cache at C:\\Users\\domstr2\\.flair\\embeddings\\pl-wiki-fasttext-300d-1M.vectors.npy\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"2021-05-12 17:02:32,864 removing temp file C:\\Users\\domstr2\\AppData\\Local\\Temp\\tmpq9mlzfps\n",
"2021-05-12 17:02:33,344 https://flair.informatik.hu-berlin.de/resources/embeddings/token/pl-wiki-fasttext-300d-1M not found in cache, downloading to C:\\Users\\domstr2\\AppData\\Local\\Temp\\tmpp2reld0s\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████| 40874795/40874795 [00:01<00:00, 21969279.66B/s]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"2021-05-12 17:02:35,412 copying C:\\Users\\domstr2\\AppData\\Local\\Temp\\tmpp2reld0s to cache at C:\\Users\\domstr2\\.flair\\embeddings\\pl-wiki-fasttext-300d-1M\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"2021-05-12 17:02:36,260 removing temp file C:\\Users\\domstr2\\AppData\\Local\\Temp\\tmpp2reld0s\n",
"2021-05-12 17:02:39,489 https://flair.informatik.hu-berlin.de/resources/embeddings/flair/lm-polish-forward-v0.2.pt not found in cache, downloading to C:\\Users\\domstr2\\AppData\\Local\\Temp\\tmpin9zi6n_\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████| 84244196/84244196 [00:03<00:00, 27120526.13B/s]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"2021-05-12 17:02:42,804 copying C:\\Users\\domstr2\\AppData\\Local\\Temp\\tmpin9zi6n_ to cache at C:\\Users\\domstr2\\.flair\\embeddings\\lm-polish-forward-v0.2.pt\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"2021-05-12 17:02:42,861 removing temp file C:\\Users\\domstr2\\AppData\\Local\\Temp\\tmpin9zi6n_\n",
"2021-05-12 17:02:43,329 https://flair.informatik.hu-berlin.de/resources/embeddings/flair/lm-polish-backward-v0.2.pt not found in cache, downloading to C:\\Users\\domstr2\\AppData\\Local\\Temp\\tmp30skh32n\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████| 84244196/84244196 [00:03<00:00, 25790261.34B/s]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"2021-05-12 17:02:46,769 copying C:\\Users\\domstr2\\AppData\\Local\\Temp\\tmp30skh32n to cache at C:\\Users\\domstr2\\.flair\\embeddings\\lm-polish-backward-v0.2.pt\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"2021-05-12 17:02:46,828 removing temp file C:\\Users\\domstr2\\AppData\\Local\\Temp\\tmp30skh32n\n"
]
}
],
"source": [ "source": [
"embedding_types = [\n", "embedding_types = [\n",
" WordEmbeddings('pl'),\n", " WordEmbeddings('pl'),\n",
@ -631,7 +397,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 35, "execution_count": 8,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -687,15 +453,15 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 36, "execution_count": 9,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"2021-05-12 17:07:41,538 ----------------------------------------------------------------------------------------------------\n", "2021-05-16 11:40:14,273 ----------------------------------------------------------------------------------------------------\n",
"2021-05-12 17:07:41,539 Model: \"SequenceTagger(\n", "2021-05-16 11:40:14,274 Model: \"SequenceTagger(\n",
" (embeddings): StackedEmbeddings(\n", " (embeddings): StackedEmbeddings(\n",
" (list_embedding_0): WordEmbeddings('pl')\n", " (list_embedding_0): WordEmbeddings('pl')\n",
" (list_embedding_1): FlairEmbeddings(\n", " (list_embedding_1): FlairEmbeddings(\n",
@ -728,53 +494,154 @@
" (weights): None\n", " (weights): None\n",
" (weight_tensor) None\n", " (weight_tensor) None\n",
")\"\n", ")\"\n",
"2021-05-12 17:07:41,540 ----------------------------------------------------------------------------------------------------\n", "2021-05-16 11:40:14,275 ----------------------------------------------------------------------------------------------------\n",
"2021-05-12 17:07:41,541 Corpus: \"Corpus: 37 train + 4 dev + 41 test sentences\"\n", "2021-05-16 11:40:14,277 Corpus: \"Corpus: 36 train + 4 dev + 40 test sentences\"\n",
"2021-05-12 17:07:41,541 ----------------------------------------------------------------------------------------------------\n", "2021-05-16 11:40:14,277 ----------------------------------------------------------------------------------------------------\n",
"2021-05-12 17:07:41,542 Parameters:\n", "2021-05-16 11:40:14,278 Parameters:\n",
"2021-05-12 17:07:41,542 - learning_rate: \"0.1\"\n", "2021-05-16 11:40:14,279 - learning_rate: \"0.1\"\n",
"2021-05-12 17:07:41,543 - mini_batch_size: \"32\"\n", "2021-05-16 11:40:14,280 - mini_batch_size: \"32\"\n",
"2021-05-12 17:07:41,543 - patience: \"3\"\n", "2021-05-16 11:40:14,280 - patience: \"3\"\n",
"2021-05-12 17:07:41,544 - anneal_factor: \"0.5\"\n", "2021-05-16 11:40:14,281 - anneal_factor: \"0.5\"\n",
"2021-05-12 17:07:41,544 - max_epochs: \"10\"\n", "2021-05-16 11:40:14,282 - max_epochs: \"10\"\n",
"2021-05-12 17:07:41,545 - shuffle: \"True\"\n", "2021-05-16 11:40:14,283 - shuffle: \"True\"\n",
"2021-05-12 17:07:41,546 - train_with_dev: \"False\"\n", "2021-05-16 11:40:14,285 - train_with_dev: \"False\"\n",
"2021-05-12 17:07:41,546 - batch_growth_annealing: \"False\"\n", "2021-05-16 11:40:14,286 - batch_growth_annealing: \"False\"\n",
"2021-05-12 17:07:41,547 ----------------------------------------------------------------------------------------------------\n", "2021-05-16 11:40:14,287 ----------------------------------------------------------------------------------------------------\n",
"2021-05-12 17:07:41,547 Model training base path: \"slot-model\"\n", "2021-05-16 11:40:14,288 Model training base path: \"slot-model\"\n",
"2021-05-12 17:07:41,548 ----------------------------------------------------------------------------------------------------\n", "2021-05-16 11:40:14,288 ----------------------------------------------------------------------------------------------------\n",
"2021-05-12 17:07:41,549 Device: cpu\n", "2021-05-16 11:40:14,289 Device: cpu\n",
"2021-05-12 17:07:41,549 ----------------------------------------------------------------------------------------------------\n", "2021-05-16 11:40:14,290 ----------------------------------------------------------------------------------------------------\n",
"2021-05-12 17:07:41,550 Embeddings storage mode: cpu\n", "2021-05-16 11:40:14,292 Embeddings storage mode: cpu\n",
"2021-05-12 17:07:41,552 ----------------------------------------------------------------------------------------------------\n", "2021-05-16 11:40:14,295 ----------------------------------------------------------------------------------------------------\n",
"2021-05-12 17:07:46,139 epoch 1 - iter 1/2 - loss 9.51263237 - samples/sec: 6.98 - lr: 0.100000\n", "2021-05-16 11:40:18,737 epoch 1 - iter 1/2 - loss 13.17695141 - samples/sec: 7.21 - lr: 0.100000\n",
"2021-05-12 17:07:47,186 epoch 1 - iter 2/2 - loss 7.22621894 - samples/sec: 30.58 - lr: 0.100000\n", "2021-05-16 11:40:19,989 epoch 1 - iter 2/2 - loss 11.51309586 - samples/sec: 25.57 - lr: 0.100000\n",
"2021-05-12 17:07:47,188 ----------------------------------------------------------------------------------------------------\n", "2021-05-16 11:40:19,989 ----------------------------------------------------------------------------------------------------\n",
"2021-05-12 17:07:47,189 EPOCH 1 done: loss 7.2262 - lr 0.1000000\n", "2021-05-16 11:40:19,989 EPOCH 1 done: loss 11.5131 - lr 0.1000000\n",
"2021-05-12 17:07:48,466 DEV : loss 5.046579837799072 - score 0.0\n", "2021-05-16 11:40:20,670 DEV : loss 5.320306777954102 - score 0.0\n",
"2021-05-12 17:07:48,468 BAD EPOCHS (no improvement): 0\n", "2021-05-16 11:40:20,671 BAD EPOCHS (no improvement): 0\n",
"saving best model\n" "saving best model\n",
"2021-05-16 11:40:30,073 ----------------------------------------------------------------------------------------------------\n",
"2021-05-16 11:40:30,802 epoch 2 - iter 1/2 - loss 8.20096970 - samples/sec: 45.04 - lr: 0.100000\n",
"2021-05-16 11:40:31,005 epoch 2 - iter 2/2 - loss 5.87843704 - samples/sec: 157.40 - lr: 0.100000\n",
"2021-05-16 11:40:31,006 ----------------------------------------------------------------------------------------------------\n",
"2021-05-16 11:40:31,008 EPOCH 2 done: loss 5.8784 - lr 0.1000000\n",
"2021-05-16 11:40:31,020 DEV : loss 2.201185703277588 - score 0.0\n",
"2021-05-16 11:40:31,038 BAD EPOCHS (no improvement): 0\n",
"saving best model\n",
"2021-05-16 11:40:40,878 ----------------------------------------------------------------------------------------------------\n",
"2021-05-16 11:40:41,800 epoch 3 - iter 1/2 - loss 3.59802794 - samples/sec: 34.83 - lr: 0.100000\n",
"2021-05-16 11:40:42,230 epoch 3 - iter 2/2 - loss 7.24588382 - samples/sec: 74.64 - lr: 0.100000\n",
"2021-05-16 11:40:42,231 ----------------------------------------------------------------------------------------------------\n",
"2021-05-16 11:40:42,233 EPOCH 3 done: loss 7.2459 - lr 0.1000000\n",
"2021-05-16 11:40:42,290 DEV : loss 2.3815672397613525 - score 0.0\n",
"2021-05-16 11:40:42,295 BAD EPOCHS (no improvement): 1\n",
"2021-05-16 11:40:42,300 ----------------------------------------------------------------------------------------------------\n",
"2021-05-16 11:40:43,662 epoch 4 - iter 1/2 - loss 4.05115032 - samples/sec: 23.57 - lr: 0.100000\n",
"2021-05-16 11:40:44,013 epoch 4 - iter 2/2 - loss 3.16846037 - samples/sec: 91.53 - lr: 0.100000\n",
"2021-05-16 11:40:44,015 ----------------------------------------------------------------------------------------------------\n",
"2021-05-16 11:40:44,018 EPOCH 4 done: loss 3.1685 - lr 0.1000000\n",
"2021-05-16 11:40:44,072 DEV : loss 1.7660648822784424 - score 0.0\n",
"2021-05-16 11:40:44,075 BAD EPOCHS (no improvement): 0\n",
"saving best model\n",
"2021-05-16 11:40:53,620 ----------------------------------------------------------------------------------------------------\n",
"2021-05-16 11:40:54,419 epoch 5 - iter 1/2 - loss 3.52825356 - samples/sec: 40.10 - lr: 0.100000\n",
"2021-05-16 11:40:54,594 epoch 5 - iter 2/2 - loss 3.12245941 - samples/sec: 183.91 - lr: 0.100000\n",
"2021-05-16 11:40:54,595 ----------------------------------------------------------------------------------------------------\n",
"2021-05-16 11:40:54,596 EPOCH 5 done: loss 3.1225 - lr 0.1000000\n",
"2021-05-16 11:40:54,624 DEV : loss 1.8835055828094482 - score 0.0\n",
"2021-05-16 11:40:54,626 BAD EPOCHS (no improvement): 1\n",
"2021-05-16 11:40:54,627 ----------------------------------------------------------------------------------------------------\n",
"2021-05-16 11:40:55,393 epoch 6 - iter 1/2 - loss 2.84318709 - samples/sec: 41.88 - lr: 0.100000\n",
"2021-05-16 11:40:55,648 epoch 6 - iter 2/2 - loss 4.79819477 - samples/sec: 125.98 - lr: 0.100000\n",
"2021-05-16 11:40:55,649 ----------------------------------------------------------------------------------------------------\n",
"2021-05-16 11:40:55,650 EPOCH 6 done: loss 4.7982 - lr 0.1000000\n",
"2021-05-16 11:40:55,675 DEV : loss 1.9106686115264893 - score 0.0\n",
"2021-05-16 11:40:55,677 BAD EPOCHS (no improvement): 2\n",
"2021-05-16 11:40:55,678 ----------------------------------------------------------------------------------------------------\n",
"2021-05-16 11:40:56,467 epoch 7 - iter 1/2 - loss 3.35292196 - samples/sec: 40.66 - lr: 0.100000\n",
"2021-05-16 11:40:56,661 epoch 7 - iter 2/2 - loss 1.90253919 - samples/sec: 165.80 - lr: 0.100000\n",
"2021-05-16 11:40:56,662 ----------------------------------------------------------------------------------------------------\n",
"2021-05-16 11:40:56,663 EPOCH 7 done: loss 1.9025 - lr 0.1000000\n",
"2021-05-16 11:40:56,689 DEV : loss 1.5785303115844727 - score 0.0\n",
"2021-05-16 11:40:56,691 BAD EPOCHS (no improvement): 0\n",
"saving best model\n",
"2021-05-16 11:41:09,226 ----------------------------------------------------------------------------------------------------\n",
"2021-05-16 11:41:10,375 epoch 8 - iter 1/2 - loss 3.24992299 - samples/sec: 27.87 - lr: 0.100000\n",
"2021-05-16 11:41:10,744 epoch 8 - iter 2/2 - loss 3.30123496 - samples/sec: 87.17 - lr: 0.100000\n",
"2021-05-16 11:41:10,745 ----------------------------------------------------------------------------------------------------\n",
"2021-05-16 11:41:10,746 EPOCH 8 done: loss 3.3012 - lr 0.1000000\n",
"2021-05-16 11:41:10,798 DEV : loss 1.590420126914978 - score 0.0\n",
"2021-05-16 11:41:10,802 BAD EPOCHS (no improvement): 1\n",
"2021-05-16 11:41:10,807 ----------------------------------------------------------------------------------------------------\n",
"2021-05-16 11:41:12,175 epoch 9 - iter 1/2 - loss 2.74546242 - samples/sec: 23.41 - lr: 0.100000\n",
"2021-05-16 11:41:12,515 epoch 9 - iter 2/2 - loss 2.34704965 - samples/sec: 94.40 - lr: 0.100000\n",
"2021-05-16 11:41:12,518 ----------------------------------------------------------------------------------------------------\n",
"2021-05-16 11:41:12,520 EPOCH 9 done: loss 2.3470 - lr 0.1000000\n",
"2021-05-16 11:41:12,573 DEV : loss 1.6068150997161865 - score 0.0\n"
] ]
}, },
{ {
"ename": "RuntimeError", "name": "stdout",
"evalue": "[enforce fail at ..\\caffe2\\serialize\\inline_container.cc:274] . unexpected pos 64 vs 0", "output_type": "stream",
"output_type": "error", "text": [
"traceback": [ "2021-05-16 11:41:12,575 BAD EPOCHS (no improvement): 2\n",
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", "2021-05-16 11:41:12,577 ----------------------------------------------------------------------------------------------------\n",
"\u001b[1;31mOSError\u001b[0m Traceback (most recent call last)", "2021-05-16 11:41:13,690 epoch 10 - iter 1/2 - loss 2.63941884 - samples/sec: 28.79 - lr: 0.100000\n",
"\u001b[1;32m~\\anaconda3\\lib\\site-packages\\torch\\serialization.py\u001b[0m in \u001b[0;36msave\u001b[1;34m(obj, f, pickle_module, pickle_protocol, _use_new_zipfile_serialization)\u001b[0m\n\u001b[0;32m 371\u001b[0m \u001b[1;32mwith\u001b[0m \u001b[0m_open_zipfile_writer\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mopened_file\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0mopened_zipfile\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 372\u001b[1;33m \u001b[0m_save\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mobj\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mopened_zipfile\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mpickle_module\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mpickle_protocol\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 373\u001b[0m \u001b[1;32mreturn\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", "2021-05-16 11:41:13,878 epoch 10 - iter 2/2 - loss 2.18226165 - samples/sec: 171.12 - lr: 0.100000\n",
"\u001b[1;32m~\\anaconda3\\lib\\site-packages\\torch\\serialization.py\u001b[0m in \u001b[0;36m_save\u001b[1;34m(obj, zip_file, pickle_module, pickle_protocol)\u001b[0m\n\u001b[0;32m 477\u001b[0m \u001b[0mdata_value\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mdata_buf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mgetvalue\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 478\u001b[1;33m \u001b[0mzip_file\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mwrite_record\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'data.pkl'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdata_value\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata_value\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 479\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", "2021-05-16 11:41:13,879 ----------------------------------------------------------------------------------------------------\n",
"\u001b[1;31mOSError\u001b[0m: [Errno 28] No space left on device", "2021-05-16 11:41:13,880 EPOCH 10 done: loss 2.1823 - lr 0.1000000\n",
"\nDuring handling of the above exception, another exception occurred:\n", "2021-05-16 11:41:13,906 DEV : loss 1.458857536315918 - score 0.0\n",
"\u001b[1;31mRuntimeError\u001b[0m Traceback (most recent call last)", "2021-05-16 11:41:13,907 BAD EPOCHS (no improvement): 0\n",
"\u001b[1;32m<ipython-input-36-6f4b58920804>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[0mtrainer\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mModelTrainer\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtagger\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcorpus\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 2\u001b[1;33m trainer.train('slot-model',\n\u001b[0m\u001b[0;32m 3\u001b[0m \u001b[0mlearning_rate\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m0.1\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4\u001b[0m \u001b[0mmini_batch_size\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m32\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5\u001b[0m \u001b[0mmax_epochs\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m10\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", "saving best model\n",
"\u001b[1;32m~\\anaconda3\\lib\\site-packages\\flair\\trainers\\trainer.py\u001b[0m in \u001b[0;36mtrain\u001b[1;34m(self, base_path, learning_rate, mini_batch_size, mini_batch_chunk_size, max_epochs, scheduler, cycle_momentum, anneal_factor, patience, initial_extra_patience, min_learning_rate, train_with_dev, train_with_test, monitor_train, monitor_test, embeddings_storage_mode, checkpoint, save_final_model, anneal_with_restarts, anneal_with_prestarts, batch_growth_annealing, shuffle, param_selection_mode, write_weights, num_workers, sampler, use_amp, amp_opt_level, eval_on_train_fraction, eval_on_train_shuffle, save_model_at_each_epoch, **kwargs)\u001b[0m\n\u001b[0;32m 592\u001b[0m ):\n\u001b[0;32m 593\u001b[0m \u001b[0mprint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"saving best model\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 594\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mmodel\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msave\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mbase_path\u001b[0m \u001b[1;33m/\u001b[0m \u001b[1;34m\"best-model.pt\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 595\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 596\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0manneal_with_prestarts\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", "2021-05-16 11:41:33,558 ----------------------------------------------------------------------------------------------------\n",
"\u001b[1;32m~\\anaconda3\\lib\\site-packages\\flair\\nn.py\u001b[0m in \u001b[0;36msave\u001b[1;34m(self, model_file)\u001b[0m\n\u001b[0;32m 70\u001b[0m \u001b[0mmodel_state\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_get_state_dict\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 71\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 72\u001b[1;33m \u001b[0mtorch\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msave\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmodel_state\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mstr\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmodel_file\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mpickle_protocol\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m4\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 73\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 74\u001b[0m \u001b[1;33m@\u001b[0m\u001b[0mclassmethod\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", "2021-05-16 11:41:33,559 Testing using best model ...\n",
"\u001b[1;32m~\\anaconda3\\lib\\site-packages\\torch\\serialization.py\u001b[0m in \u001b[0;36msave\u001b[1;34m(obj, f, pickle_module, pickle_protocol, _use_new_zipfile_serialization)\u001b[0m\n\u001b[0;32m 371\u001b[0m \u001b[1;32mwith\u001b[0m \u001b[0m_open_zipfile_writer\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mopened_file\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0mopened_zipfile\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 372\u001b[0m \u001b[0m_save\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mobj\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mopened_zipfile\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mpickle_module\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mpickle_protocol\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 373\u001b[1;33m \u001b[1;32mreturn\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 374\u001b[0m \u001b[0m_legacy_save\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mobj\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mopened_file\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mpickle_module\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mpickle_protocol\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 375\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", "2021-05-16 11:41:33,560 loading file slot-model\\best-model.pt\n",
"\u001b[1;32m~\\anaconda3\\lib\\site-packages\\torch\\serialization.py\u001b[0m in \u001b[0;36m__exit__\u001b[1;34m(self, *args)\u001b[0m\n\u001b[0;32m 257\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 258\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m__exit__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m->\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 259\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfile_like\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mwrite_end_of_file\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 260\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mbuffer\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mflush\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 261\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", "2021-05-16 11:41:45,502 0.1765\t0.1667\t0.1714\n",
"\u001b[1;31mRuntimeError\u001b[0m: [enforce fail at ..\\caffe2\\serialize\\inline_container.cc:274] . unexpected pos 64 vs 0" "2021-05-16 11:41:45,503 \n",
"Results:\n",
"- F1-score (micro) 0.1714\n",
"- F1-score (macro) 0.1161\n",
"\n",
"By class:\n",
"appoinment/doctor tp: 1 - fp: 9 - fn: 5 - precision: 0.1000 - recall: 0.1667 - f1-score: 0.1250\n",
"appointment/type tp: 0 - fp: 0 - fn: 2 - precision: 0.0000 - recall: 0.0000 - f1-score: 0.0000\n",
"datetime tp: 0 - fp: 1 - fn: 3 - precision: 0.0000 - recall: 0.0000 - f1-score: 0.0000\n",
"login/id tp: 2 - fp: 2 - fn: 1 - precision: 0.5000 - recall: 0.6667 - f1-score: 0.5714\n",
"login/password tp: 0 - fp: 0 - fn: 3 - precision: 0.0000 - recall: 0.0000 - f1-score: 0.0000\n",
"prescription/type tp: 0 - fp: 2 - fn: 1 - precision: 0.0000 - recall: 0.0000 - f1-score: 0.0000\n",
"2021-05-16 11:41:45,503 ----------------------------------------------------------------------------------------------------\n"
] ]
},
{
"data": {
"text/plain": [
"{'test_score': 0.17142857142857143,\n",
" 'dev_score_history': [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0],\n",
" 'train_loss_history': [11.51309585571289,\n",
" 5.878437042236328,\n",
" 7.245883822441101,\n",
" 3.1684603691101074,\n",
" 3.1224594116210938,\n",
" 4.798194766044617,\n",
" 1.9025391936302185,\n",
" 3.3012349605560303,\n",
" 2.347049653530121,\n",
" 2.182261645793915],\n",
" 'dev_loss_history': [5.320306777954102,\n",
" 2.201185703277588,\n",
" 2.3815672397613525,\n",
" 1.7660648822784424,\n",
" 1.8835055828094482,\n",
" 1.9106686115264893,\n",
" 1.5785303115844727,\n",
" 1.590420126914978,\n",
" 1.6068150997161865,\n",
" 1.458857536315918]}"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
} }
], ],
"source": [ "source": [
@ -829,14 +696,14 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 19, "execution_count": 10,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"2021-05-12 16:58:59,033 loading file slot-model/final-model.pt\n" "2021-05-16 11:41:45,529 loading file slot-model/final-model.pt\n"
] ]
} }
], ],
@ -854,7 +721,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 20, "execution_count": 11,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -875,7 +742,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 23, "execution_count": 20,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -883,29 +750,29 @@
"text/html": [ "text/html": [
"<table>\n", "<table>\n",
"<tbody>\n", "<tbody>\n",
"<tr><td>doktor </td><td>O</td></tr>\n", "<tr><td>doktor </td><td>I-appoinment/doctor</td></tr>\n",
"<tr><td>lekarz </td><td>O</td></tr>\n", "<tr><td>lekarza </td><td>B-appoinment/doctor</td></tr>\n",
"<tr><td>wizyta </td><td>O</td></tr>\n", "<tr><td>rodzinnego </td><td>O </td></tr>\n",
"<tr><td>kolano </td><td>O</td></tr>\n", "<tr><td>najlepiej </td><td>O </td></tr>\n",
"<tr><td>na </td><td>O</td></tr>\n", "<tr><td>dzisiaj </td><td>O </td></tr>\n",
"<tr><td>godzine</td><td>O</td></tr>\n", "<tr><td>w </td><td>O </td></tr>\n",
"<tr><td>jutro </td><td>O</td></tr>\n", "<tr><td>godzinach </td><td>O </td></tr>\n",
"<tr><td>dzisiaj</td><td>O</td></tr>\n", "<tr><td>popołudniowych</td><td>O </td></tr>\n",
"<tr><td>13:00 </td><td>O</td></tr>\n", "<tr><td>dziś </td><td>O </td></tr>\n",
"</tbody>\n", "</tbody>\n",
"</table>" "</table>"
], ],
"text/plain": [ "text/plain": [
"'<table>\\n<tbody>\\n<tr><td>doktor </td><td>O</td></tr>\\n<tr><td>lekarz </td><td>O</td></tr>\\n<tr><td>wizyta </td><td>O</td></tr>\\n<tr><td>kolano </td><td>O</td></tr>\\n<tr><td>na </td><td>O</td></tr>\\n<tr><td>godzine</td><td>O</td></tr>\\n<tr><td>jutro </td><td>O</td></tr>\\n<tr><td>dzisiaj</td><td>O</td></tr>\\n<tr><td>13:00 </td><td>O</td></tr>\\n</tbody>\\n</table>'" "'<table>\\n<tbody>\\n<tr><td>doktor </td><td>I-appoinment/doctor</td></tr>\\n<tr><td>lekarza </td><td>B-appoinment/doctor</td></tr>\\n<tr><td>rodzinnego </td><td>O </td></tr>\\n<tr><td>najlepiej </td><td>O </td></tr>\\n<tr><td>dzisiaj </td><td>O </td></tr>\\n<tr><td>w </td><td>O </td></tr>\\n<tr><td>godzinach </td><td>O </td></tr>\\n<tr><td>popołudniowych</td><td>O </td></tr>\\n<tr><td>dziś </td><td>O </td></tr>\\n</tbody>\\n</table>'"
] ]
}, },
"execution_count": 23, "execution_count": 20,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
], ],
"source": [ "source": [
"tabulate(predict(model, 'doktor lekarz wizyta kolano na godzine jutro dzisiaj 13:00'.split()), tablefmt='html')" "tabulate(predict(model, 'doktor lekarza rodzinnego najlepiej dzisiaj w godzinach popołudniowych dziś '.split()), tablefmt='html')"
] ]
}, },
{ {
@ -920,6 +787,13 @@
" 4. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin, Attention is All you Need, NIPS 2017, pp. 5998-6008, https://arxiv.org/abs/1706.03762\n", " 4. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin, Attention is All you Need, NIPS 2017, pp. 5998-6008, https://arxiv.org/abs/1706.03762\n",
" 5. Alan Akbik, Duncan Blythe, Roland Vollgraf, Contextual String Embeddings for Sequence Labeling, Proceedings of the 27th International Conference on Computational Linguistics, pp. 16381649, https://www.aclweb.org/anthology/C18-1139.pdf\n" " 5. Alan Akbik, Duncan Blythe, Roland Vollgraf, Contextual String Embeddings for Sequence Labeling, Proceedings of the 27th International Conference on Computational Linguistics, pp. 16381649, https://www.aclweb.org/anthology/C18-1139.pdf\n"
] ]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
} }
], ],
"metadata": { "metadata": {

View File

@ -3,11 +3,11 @@
# slots: # slots:
1 hej greeting NoLabel 1 hej greeting NoLabel
# text: Dzień dobry, chciałbym umówić się na wizytę do lekarza rodzinnego. Najlepiej dzisiaj w godzinach popołudniowych. # text: Dzień dobry chciałbym umówić się na wizytę do lekarza rodzinnego Najlepiej dzisiaj w godzinach popołudniowych
# intent: appoinment/create_appointment # intent: appoinment/create_appointment
# slots: # slots:
1 dzień appoinment/create_appointment NoLabel 1 dzień appoinment/create_appointment NoLabel
2 dobry, appoinment/create_appointment NoLabel 2 dobry appoinment/create_appointment NoLabel
3 chciałbym appoinment/create_appointment NoLabel 3 chciałbym appoinment/create_appointment NoLabel
4 umówić appoinment/create_appointment NoLabel 4 umówić appoinment/create_appointment NoLabel
5 się appoinment/create_appointment NoLabel 5 się appoinment/create_appointment NoLabel
@ -15,12 +15,12 @@
7 wizytę appoinment/create_appointment NoLabel 7 wizytę appoinment/create_appointment NoLabel
8 do appoinment/create_appointment NoLabel 8 do appoinment/create_appointment NoLabel
9 lekarza appoinment/create_appointment B-appoinment/doctor 9 lekarza appoinment/create_appointment B-appoinment/doctor
10 rodzinnego. appoinment/create_appointment I-appoinment/doctor 10 rodzinnego appoinment/create_appointment I-appoinment/doctor
11 najlepiej appoinment/create_appointment NoLabel 11 najlepiej appoinment/create_appointment NoLabel
12 dzisiaj appoinment/create_appointment B-datetime 12 dzisiaj appoinment/create_appointment B-datetime
13 w appoinment/create_appointment I-datetime 13 w appoinment/create_appointment I-datetime
14 godzinach appoinment/create_appointment I-datetime 14 godzinach appoinment/create_appointment I-datetime
15 popołudniowych. appoinment/create_appointment I-datetime 15 popołudniowych appoinment/create_appointment I-datetime
# text: 12345678AFD # text: 12345678AFD
# intent: login/enter_id # intent: login/enter_id
@ -52,16 +52,16 @@
1 ten appoinment/confirm NoLabel 1 ten appoinment/confirm NoLabel
2 termin appoinment/confirm NoLabel 2 termin appoinment/confirm NoLabel
3 mi appoinment/confirm NoLabel 3 mi appoinment/confirm NoLabel
4 odpowiada! appoinment/confirm NoLabel 4 odpowiada appoinment/confirm NoLabel
# text: Tak, bardzo dziękuję. # text: Tak bardzo dziękuję
# intent: affirm # intent: affirm
# slots: # slots:
1 tak, affirm NoLabel 1 tak affirm NoLabel
2 bardzo affirm NoLabel 2 bardzo affirm NoLabel
3 dziękuję. affirm NoLabel 3 dziękuję affirm NoLabel
# text: Chciałbym też od razu zrobić badania morfologii krwi. Kiedy mogę przyjść na pobranie krwi? # text: Chciałbym też od razu zrobić badania morfologii krwi Kiedy mogę przyjść na pobranie krwi?
# intent: appoinment/create_appointment request_information/opening_hours # intent: appoinment/create_appointment request_information/opening_hours
# slots: # slots:
1 chciałbym appoinment/create_appointment NoLabel 1 chciałbym appoinment/create_appointment NoLabel
@ -71,26 +71,26 @@
5 zrobić appoinment/create_appointment NoLabel 5 zrobić appoinment/create_appointment NoLabel
6 badania appoinment/create_appointment B-appointment/type 6 badania appoinment/create_appointment B-appointment/type
7 morfologii appoinment/create_appointment I-appointment/type 7 morfologii appoinment/create_appointment I-appointment/type
8 krwi. appoinment/create_appointment I-appointment/type 8 krwi appoinment/create_appointment I-appointment/type
9 kiedy request_information/opening_hours NoLabel 9 kiedy request_information/opening_hours NoLabel
10 mogę request_information/opening_hours NoLabel 10 mogę request_information/opening_hours NoLabel
11 przyjść request_information/opening_hours NoLabel 11 przyjść request_information/opening_hours NoLabel
12 na request_information/opening_hours NoLabel 12 na request_information/opening_hours NoLabel
13 pobranie request_information/opening_hours B-appointment/type 13 pobranie request_information/opening_hours B-appointment/type
14 krwi? request_information/opening_hours I-appointment/type 14 krwi request_information/opening_hours I-appointment/type
# text: Dziękuję bardzo za informację. W takim przypadku to wszystko. # text: Dziękuję bardzo za informację W takim przypadku to wszystko
# intent: end_conversation # intent: end_conversation
# slots: # slots:
1 dziękuję end_conversation NoLabel 1 dziękuję end_conversation NoLabel
2 bardzo end_conversation NoLabel 2 bardzo end_conversation NoLabel
3 za end_conversation NoLabel 3 za end_conversation NoLabel
4 informację. end_conversation NoLabel 4 informację end_conversation NoLabel
5 w end_conversation NoLabel 5 w end_conversation NoLabel
6 takim end_conversation NoLabel 6 takim end_conversation NoLabel
7 przypadku end_conversation NoLabel 7 przypadku end_conversation NoLabel
8 to end_conversation NoLabel 8 to end_conversation NoLabel
9 wszystko. end_conversation NoLabel 9 wszystko end_conversation NoLabel
# text: Dzień dobry # text: Dzień dobry
# intent: greeting # intent: greeting
@ -141,10 +141,10 @@
# slots: # slots:
1 tak affirm NoLabel 1 tak affirm NoLabel
# text: 12.04.2021 # text: 12042021
# intent: appoinment/set_date # intent: appoinment/set_date
# slots: # slots:
1 12.04.2021 appoinment/set_date B-datetime 1 12042021 appoinment/set_date B-datetime
# text: 13:00 # text: 13:00
# intent: appoinment/set_time # intent: appoinment/set_time
@ -176,17 +176,17 @@
# slots: # slots:
1 cześć greeting NoLabel 1 cześć greeting NoLabel
# text: Chciałbym się dowiedzieć, czy mam umówione jakieś wizyty. # text: Chciałbym się dowiedzieć czy mam umówione jakieś wizyty
# intent: appoinment/check_appointments # intent: appoinment/check_appointments
# slots: # slots:
1 chciałbym appoinment/check_appointments NoLabel 1 chciałbym appoinment/check_appointments NoLabel
2 się appoinment/check_appointments NoLabel 2 się appoinment/check_appointments NoLabel
3 dowiedzieć, appoinment/check_appointments NoLabel 3 dowiedzieć appoinment/check_appointments NoLabel
4 czy appoinment/check_appointments NoLabel 4 czy appoinment/check_appointments NoLabel
5 mam appoinment/check_appointments NoLabel 5 mam appoinment/check_appointments NoLabel
6 umówione appoinment/check_appointments NoLabel 6 umówione appoinment/check_appointments NoLabel
7 jakieś appoinment/check_appointments NoLabel 7 jakieś appoinment/check_appointments NoLabel
8 wizyty. appoinment/check_appointments NoLabel 8 wizyty appoinment/check_appointments NoLabel
# text: 34534535 # text: 34534535
# intent: login/enter_id # intent: login/enter_id
@ -223,7 +223,7 @@
6 państwa request_information/doctors NoLabel 6 państwa request_information/doctors NoLabel
7 przychodni? request_information/doctors NoLabel 7 przychodni? request_information/doctors NoLabel
# text: Chciałbym umówić wizytę do doktora Kolano. # text: Chciałbym umówić wizytę do doktora Kolano
# intent: appoinment/create_appointment # intent: appoinment/create_appointment
# slots: # slots:
1 chciałbym appoinment/create_appointment NoLabel 1 chciałbym appoinment/create_appointment NoLabel
@ -231,35 +231,34 @@
3 wizytę appoinment/create_appointment NoLabel 3 wizytę appoinment/create_appointment NoLabel
4 do appoinment/create_appointment NoLabel 4 do appoinment/create_appointment NoLabel
5 doktora appoinment/create_appointment B-appoinment/doctor 5 doktora appoinment/create_appointment B-appoinment/doctor
6 kolano. appoinment/create_appointment I-appoinment/doctor 6 kolano appoinment/create_appointment I-appoinment/doctor
# text: Ten termin mi odpowiada. # text: Ten termin mi odpowiada
# intent: appoinment/confirm # intent: appoinment/confirm
# slots: # slots:
1 ten appoinment/confirm NoLabel 1 ten appoinment/confirm NoLabel
2 termin appoinment/confirm NoLabel 2 termin appoinment/confirm NoLabel
3 mi appoinment/confirm NoLabel 3 mi appoinment/confirm NoLabel
4 odpowiada. appoinment/confirm NoLabel 4 odpowiada appoinment/confirm NoLabel
# text: tak # text: tak
# intent: affirm # intent: affirm
# slots: # slots:
1 tak affirm NoLabel 1 tak affirm NoLabel
# text: Nie, to wszystko. Do widzenia. # text: Nie to wszystko Do widzenia
# intent: end_conversation # intent: end_conversation
# slots: # slots:
1 nie, end_conversation NoLabel 1 nie end_conversation NoLabel
2 to end_conversation NoLabel 2 to end_conversation NoLabel
3 wszystko. end_conversation NoLabel 3 wszystko end_conversation NoLabel
4 do end_conversation NoLabel 4 do end_conversation NoLabel
5 widzenia. end_conversation NoLabel 5 widzenia end_conversation NoLabel
# text: Cześć :) # text: Cześć
# intent: greeting # intent: greeting
# slots: # slots:
1 cześć greeting NoLabel 1 cześć greeting NoLabel
2 :) greeting NoLabel
# text: Jakie usługi medyczne są dostępne? # text: Jakie usługi medyczne są dostępne?
# intent: request_information/medical_services # intent: request_information/medical_services
@ -268,54 +267,44 @@
2 usługi request_information/medical_services NoLabel 2 usługi request_information/medical_services NoLabel
3 medyczne request_information/medical_services NoLabel 3 medyczne request_information/medical_services NoLabel
4 są request_information/medical_services NoLabel 4 są request_information/medical_services NoLabel
5 dostępne? request_information/medical_services NoLabel 5 dostępne request_information/medical_services NoLabel
# text: Chciałbym zapisać się do okulisty. Ile kosztuje wizyta? # text: Chciałbym zapisać się do okulisty Ile kosztuje wizyta?
# intent: appoinment/create_appointment request_information/cost # intent: appoinment/create_appointment request_information/cost
# slots: # slots:
1 chciałbym appoinment/create_appointment NoLabel 1 chciałbym appoinment/create_appointment NoLabel
2 zapisać appoinment/create_appointment NoLabel 2 zapisać appoinment/create_appointment NoLabel
3 się appoinment/create_appointment NoLabel 3 się appoinment/create_appointment NoLabel
4 do appoinment/create_appointment NoLabel 4 do appoinment/create_appointment NoLabel
5 okulisty. appoinment/create_appointment B-appoinment/doctor 5 okulisty appoinment/create_appointment B-appoinment/doctor
6 ile request_information/cost NoLabel 6 ile request_information/cost NoLabel
7 kosztuje request_information/cost NoLabel 7 kosztuje request_information/cost NoLabel
8 wizyta? request_information/cost NoLabel 8 wizyta request_information/cost NoLabel
# text: Nie? # text: Nie ten jest idealny
# intent: deny
# slots:
1 nie? deny NoLabel
# text: Nie, ten jest idealny.
# intent: affirm # intent: affirm
# slots: # slots:
1 nie, affirm NoLabel 1 nie affirm NoLabel
2 ten affirm NoLabel 2 ten affirm NoLabel
3 jest affirm NoLabel 3 jest affirm NoLabel
4 idealny. affirm NoLabel 4 idealny affirm NoLabel
# text: Tak. # text: Tak
# intent: affirm # intent: affirm
# slots: # slots:
1 tak. affirm NoLabel 1 tak affirm NoLabel
# text: Dziękuję za informację : ). # text: Dziękuję za informację
# intent: end_conversation # intent: end_conversation
# slots: # slots:
1 dziękuję end_conversation NoLabel 1 dziękuję end_conversation NoLabel
2 za end_conversation NoLabel 2 za end_conversation NoLabel
3 informację end_conversation NoLabel 3 informację end_conversation NoLabel
4 : end_conversation NoLabel
5 ). end_conversation NoLabel
# text: Nie, dziękuję - to wszystko : ). # text: Nie dziękuję to wszystko
# intent: end_conversation # intent: end_conversation
# slots: # slots:
1 nie, end_conversation NoLabel 1 nie end_conversation NoLabel
2 dziękuję end_conversation NoLabel 2 dziękuję end_conversation NoLabel
3 - end_conversation NoLabel
4 to end_conversation NoLabel 4 to end_conversation NoLabel
5 wszystko end_conversation NoLabel 5 wszystko end_conversation NoLabel
6 : end_conversation NoLabel
7 ). end_conversation NoLabel