s495726/KWT-2024
1
0
Fork 0
forked from bfijalkowski/KWT-2024
Code Pull Requests Activity

wip

Browse Source
This commit is contained in:
Patryk Osiński 2024-04-20 19:58:36 +02:00
parent ddd2833663
commit 78982a4f21
5 changed files with 319 additions and 172 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
lab/lab_01.ipynb
View File

@ -103,7 +103,9 @@
"outputs": [ "outputs": [
{ {
"data": { "data": {
"text/plain": "['Press the ENTER button']" "text/plain": [
"['Press the ENTER button']"
]
}, },
"execution_count": 7, "execution_count": 7,
"metadata": {}, "metadata": {},
@ -168,7 +170,9 @@
"outputs": [ "outputs": [
{ {
"data": { "data": {
"text/plain": "['Press the ENTER button', 'Press the ENTER key']" "text/plain": [
"['Press the ENTER button', 'Press the ENTER key']"
]
}, },
"execution_count": 9, "execution_count": 9,
"metadata": {}, "metadata": {},
@ -208,7 +212,9 @@
"outputs": [ "outputs": [
{ {
"data": { "data": {
"text/plain": "[]" "text/plain": [
"[]"
]
}, },
"execution_count": 10, "execution_count": 10,
"metadata": {}, "metadata": {},
@ -273,7 +279,9 @@
"outputs": [ "outputs": [
{ {
"data": { "data": {
"text/plain": "[]" "text/plain": [
"[]"
]
}, },
"execution_count": 22, "execution_count": 22,
"metadata": {}, "metadata": {},
@ -335,7 +343,9 @@
"outputs": [ "outputs": [
{ {
"data": { "data": {
"text/plain": "[]" "text/plain": [
"[]"
]
}, },
"execution_count": 24, "execution_count": 24,
"metadata": {}, "metadata": {},
@ -478,7 +488,9 @@
"outputs": [ "outputs": [
{ {
"data": { "data": {
"text/plain": "[('przycisk', 'button'), ('drukarka', 'printer')]" "text/plain": [
"[('przycisk', 'button'), ('drukarka', 'printer')]"
]
}, },
"execution_count": 28, "execution_count": 28,
"metadata": {}, "metadata": {},
@ -585,7 +597,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.10.11" "version": "3.9.2"
}, },
"subtitle": "1. Podstawowe techniki wspomagania tłumaczenia", "subtitle": "1. Podstawowe techniki wspomagania tłumaczenia",
"title": "Komputerowe wspomaganie tłumaczenia", "title": "Komputerowe wspomaganie tłumaczenia",

92
lab/lab_02.ipynb
View File

@ -40,9 +40,11 @@
] ]
}, },
{ {
"cell_type": "markdown", "cell_type": "code",
"id": "existing-approval", "execution_count": null,
"id": "961796fd-4463-4a17-ac15-afe712b3959e",
"metadata": {}, "metadata": {},
"outputs": [],
"source": [ "source": [
"Jedną z funkcji dostępnych we wszystkich większych programach do wspomagania tłumaczenia jest znajdowanie bardzo pewnych dopasowań w pamięci tłumaczeń. Są one zwane **ICE** (In-Context Exact match) lub 101% match. Są to takie dopasowania z pamięci tłumaczeń, dla których nie tylko zdanie źródłowe z TM jest identyczne z tłumaczonym, ale także poprzednie zdanie źródłowe z TM zgadza się z poprzednim zdaniem tłumaczonym oraz następne z TM z następnym tłumaczonym." "Jedną z funkcji dostępnych we wszystkich większych programach do wspomagania tłumaczenia jest znajdowanie bardzo pewnych dopasowań w pamięci tłumaczeń. Są one zwane **ICE** (In-Context Exact match) lub 101% match. Są to takie dopasowania z pamięci tłumaczeń, dla których nie tylko zdanie źródłowe z TM jest identyczne z tłumaczonym, ale także poprzednie zdanie źródłowe z TM zgadza się z poprzednim zdaniem tłumaczonym oraz następne z TM z następnym tłumaczonym."
] ]
@ -85,8 +87,31 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"def exact_match(sentence):\n",
" for key, entry in enumerate(translation_memory):\n",
" if entry[0] == sentence:\n",
" return key, entry[1]\n",
" return None, None\n",
"\n",
"\n",
"def has_exact_match_on_index(index, sentence):\n",
" return translation_memory[index][0] == sentence\n",
"\n",
"\n",
"def ice_lookup(sentence, prev_sentence, next_sentence):\n", "def ice_lookup(sentence, prev_sentence, next_sentence):\n",
" return []" " index, match = exact_match(sentence)\n",
" trans_length = len(translation_memory)\n",
" if index is None:\n",
" return []\n",
" if next_sentence \\\n",
" and index < trans_length \\\n",
" and not has_exact_match_on_index(index + 1, next_sentence):\n",
" return []\n",
" if prev_sentence \\\n",
" and index > 0 \\\n",
" and not has_exact_match_on_index(index - 1, prev_sentence):\n",
" return []\n",
" return [match]"
] ]
}, },
{ {
@ -141,7 +166,7 @@
"id": "graduate-theorem", "id": "graduate-theorem",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Odpowiedź:" "Odpowiedź: Nie. 1, 3, 4."
] ]
}, },
{ {
@ -179,7 +204,7 @@
"id": "metallic-leave", "id": "metallic-leave",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Odpowiedź:" "Odpowiedź: Tak. 1, 2, 3, 4."
] ]
}, },
{ {
@ -206,7 +231,17 @@
"id": "bibliographic-stopping", "id": "bibliographic-stopping",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Odpowiedź:" "Odpowiedź: Tak.\n",
"1. Liczba operacji wykonanych nie może być ujemna.\n",
"2. Gdy x == y, nie są wymagane żadne operacje edycyjne, więc wynik funkcji to 0.\n",
"3. Zmiana jednego łańcucha znaków w drugi, wymaga tyle samo operacji edycji, co zmiana drugiego w pierwszy.\n",
" Studia -> Studiel = 2; Studiel -> Studia = 2; 2 == 2\n",
"4. Istnieją trzy opcje\n",
" - Jeżeli x == y == z, więc 0 + 0 == 0\n",
" - Jeżeli x == y, x != z, a x -> z = n, to y -> z = n więc albo 0 + n == n, albo n + n > 0\n",
" - Jeżeli x != y != z to im z jest bliżej do x, tym jest dalej od y (jednostką odległości jest liczba przekształceń). Można by to przedstawić graficznie jako trójkąt (x, y, z). z stanowi punkt na pośredniej drodze pomiędzy x i y, która nie może być dłuższa niż droga bezpośrednia - wynika to z własności trójkąta.\n",
" Studia -> Studiel = 2; Studiel -> udia = 4; udia -> Studia = 2;\n",
" 2 + 4 > 2; 2 + 2 == 4"
] ]
}, },
{ {
@ -214,6 +249,7 @@
"id": "attended-channels", "id": "attended-channels",
"metadata": {}, "metadata": {},
"source": [ "source": [
"\n",
"W Pythonie dostępna jest biblioteka zawierająca implementację dystansu Levenshteina. Zainstaluj ją w swoim systemie przy użyciu polecenia:\n", "W Pythonie dostępna jest biblioteka zawierająca implementację dystansu Levenshteina. Zainstaluj ją w swoim systemie przy użyciu polecenia:\n",
"\n", "\n",
"`pip3 install python-Levenshtein`\n", "`pip3 install python-Levenshtein`\n",
@ -223,21 +259,10 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 5, "execution_count": null,
"id": "secondary-wrist", "id": "355e4914-08da-4bd4-b8a2-67b055831c30",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [],
{
"data": {
"text/plain": [
"2"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [ "source": [
"from Levenshtein import distance as levenshtein_distance\n", "from Levenshtein import distance as levenshtein_distance\n",
"\n", "\n",
@ -314,22 +339,9 @@
] ]
}, },
{ {
"cell_type": "code", "cell_type": "raw",
"execution_count": 9, "id": "4a47854f-df2e-451f-8e09-99f59210f86f",
"id": "invisible-cambodia",
"metadata": {}, "metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.631578947368421"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [ "source": [
"levenshtein_similarity('Spróbuj wyłączyć i włączyć komputer', 'Nie próbuj wyłączać i włączać drukarki')" "levenshtein_similarity('Spróbuj wyłączyć i włączyć komputer', 'Nie próbuj wyłączać i włączać drukarki')"
] ]
@ -350,7 +362,11 @@
"outputs": [], "outputs": [],
"source": [ "source": [
"def fuzzy_lookup(sentence, threshold):\n", "def fuzzy_lookup(sentence, threshold):\n",
" return []" " results = []\n",
" for entry in translation_memory:\n",
" if levenshtein_similarity(entry[0], sentence) >= threshold:\n",
" results.append(entry[1])\n",
" return results"
] ]
} }
], ],
@ -358,7 +374,7 @@
"author": "Rafał Jaworski", "author": "Rafał Jaworski",
"email": "rjawor@amu.edu.pl", "email": "rjawor@amu.edu.pl",
"kernelspec": { "kernelspec": {
"display_name": "Python 3", "display_name": "Python 3 (ipykernel)",
"language": "python", "language": "python",
"name": "python3" "name": "python3"
}, },
@ -373,7 +389,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.8.10" "version": "3.9.2"
}, },
"subtitle": "2. Zaawansowane użycie pamięci tłumaczeń", "subtitle": "2. Zaawansowane użycie pamięci tłumaczeń",
"title": "Komputerowe wspomaganie tłumaczenia", "title": "Komputerowe wspomaganie tłumaczenia",

189
lab/lab_03.ipynb
View File

@ -63,7 +63,7 @@
"id": "diverse-sunglasses", "id": "diverse-sunglasses",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Odpowiedź:" "Odpowiedź: \"metal cabinet guides\". https://translate.google.pl/"
] ]
}, },
{ {
@ -115,7 +115,7 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"dictionary = ['program', 'application', 'applet' 'compile']" "dictionary = ['program', 'application', 'applet', 'compile']"
] ]
}, },
{ {
@ -133,8 +133,18 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"import re\n",
"\n",
"def terminology_lookup():\n", "def terminology_lookup():\n",
" return []" " result = []\n",
" regex = ''\n",
" for word in dictionary:\n",
" if regex != '':\n",
" regex += '|'\n",
" regex += '(' + word + ')'\n",
" for occurrence in re.finditer(regex, text, re.I):\n",
" result.append((occurrence.group(), occurrence.start(), occurrence.end()))\n",
" return result"
] ]
}, },
{ {
@ -161,116 +171,34 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 4, "execution_count": 1,
"id": "tribal-attention", "id": "tribal-attention",
"metadata": {}, "metadata": {
"ExecuteTime": {
"end_time": "2024-04-20T15:23:32.727687100Z",
"start_time": "2024-04-20T15:23:24.826454500Z"
}
},
"outputs": [ "outputs": [
{ {
"name": "stdout", "ename": "KeyboardInterrupt",
"output_type": "stream", "evalue": "",
"text": [ "output_type": "error",
" \n", "traceback": [
"for\n", "\u001B[1;31m---------------------------------------------------------------------------\u001B[0m",
"all\n", "\u001B[1;31mKeyboardInterrupt\u001B[0m Traceback (most recent call last)",
"Java\n", "Cell \u001B[1;32mIn[1], line 1\u001B[0m\n\u001B[1;32m----> 1\u001B[0m \u001B[38;5;28;01mimport\u001B[39;00m \u001B[38;5;21;01mspacy\u001B[39;00m\n\u001B[0;32m 2\u001B[0m nlp \u001B[38;5;241m=\u001B[39m spacy\u001B[38;5;241m.\u001B[39mload(\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124men_core_web_sm\u001B[39m\u001B[38;5;124m\"\u001B[39m)\n\u001B[0;32m 4\u001B[0m doc \u001B[38;5;241m=\u001B[39m nlp(text)\n",
"programmer\n", "File \u001B[1;32mj:\\.AppData\\Python\\Python310\\site-packages\\spacy\\__init__.py:13\u001B[0m\n\u001B[0;32m 10\u001B[0m \u001B[38;5;66;03m# These are imported as part of the API\u001B[39;00m\n\u001B[0;32m 11\u001B[0m \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;21;01mthinc\u001B[39;00m\u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01mapi\u001B[39;00m \u001B[38;5;28;01mimport\u001B[39;00m Config, prefer_gpu, require_cpu, require_gpu \u001B[38;5;66;03m# noqa: F401\u001B[39;00m\n\u001B[1;32m---> 13\u001B[0m \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;21;01m.\u001B[39;00m \u001B[38;5;28;01mimport\u001B[39;00m pipeline \u001B[38;5;66;03m# noqa: F401\u001B[39;00m\n\u001B[0;32m 14\u001B[0m \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;21;01m.\u001B[39;00m \u001B[38;5;28;01mimport\u001B[39;00m util\n\u001B[0;32m 15\u001B[0m \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01mabout\u001B[39;00m \u001B[38;5;28;01mimport\u001B[39;00m __version__ \u001B[38;5;66;03m# noqa: F401\u001B[39;00m\n",
":\n", "File \u001B[1;32mj:\\.AppData\\Python\\Python310\\site-packages\\spacy\\pipeline\\__init__.py:1\u001B[0m\n\u001B[1;32m----> 1\u001B[0m \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01mattributeruler\u001B[39;00m \u001B[38;5;28;01mimport\u001B[39;00m AttributeRuler\n\u001B[0;32m 2\u001B[0m \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01mdep_parser\u001B[39;00m \u001B[38;5;28;01mimport\u001B[39;00m DependencyParser\n\u001B[0;32m 3\u001B[0m \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01medit_tree_lemmatizer\u001B[39;00m \u001B[38;5;28;01mimport\u001B[39;00m EditTreeLemmatizer\n",
"this\n", "File \u001B[1;32mj:\\.AppData\\Python\\Python310\\site-packages\\spacy\\pipeline\\attributeruler.py:8\u001B[0m\n\u001B[0;32m 6\u001B[0m \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01m.\u001B[39;00m \u001B[38;5;28;01mimport\u001B[39;00m util\n\u001B[0;32m 7\u001B[0m \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01merrors\u001B[39;00m \u001B[38;5;28;01mimport\u001B[39;00m Errors\n\u001B[1;32m----> 8\u001B[0m \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01mlanguage\u001B[39;00m \u001B[38;5;28;01mimport\u001B[39;00m Language\n\u001B[0;32m 9\u001B[0m \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01mmatcher\u001B[39;00m \u001B[38;5;28;01mimport\u001B[39;00m Matcher\n\u001B[0;32m 10\u001B[0m \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01mscorer\u001B[39;00m \u001B[38;5;28;01mimport\u001B[39;00m Scorer\n",
"section\n", "File \u001B[1;32mj:\\.AppData\\Python\\Python310\\site-packages\\spacy\\language.py:43\u001B[0m\n\u001B[0;32m 41\u001B[0m \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01mlang\u001B[39;00m\u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01mtokenizer_exceptions\u001B[39;00m \u001B[38;5;28;01mimport\u001B[39;00m BASE_EXCEPTIONS, URL_MATCH\n\u001B[0;32m 42\u001B[0m \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01mlookups\u001B[39;00m \u001B[38;5;28;01mimport\u001B[39;00m load_lookups\n\u001B[1;32m---> 43\u001B[0m \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01mpipe_analysis\u001B[39;00m \u001B[38;5;28;01mimport\u001B[39;00m analyze_pipes, print_pipe_analysis, validate_attrs\n\u001B[0;32m 44\u001B[0m \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01mschemas\u001B[39;00m \u001B[38;5;28;01mimport\u001B[39;00m (\n\u001B[0;32m 45\u001B[0m ConfigSchema,\n\u001B[0;32m 46\u001B[0m ConfigSchemaInit,\n\u001B[1;32m (...)\u001B[0m\n\u001B[0;32m 49\u001B[0m validate_init_settings,\n\u001B[0;32m 50\u001B[0m )\n\u001B[0;32m 51\u001B[0m \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01mscorer\u001B[39;00m \u001B[38;5;28;01mimport\u001B[39;00m Scorer\n",
"explain\n", "File \u001B[1;32mj:\\.AppData\\Python\\Python310\\site-packages\\spacy\\pipe_analysis.py:6\u001B[0m\n\u001B[0;32m 3\u001B[0m \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;21;01mwasabi\u001B[39;00m \u001B[38;5;28;01mimport\u001B[39;00m msg\n\u001B[0;32m 5\u001B[0m \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01merrors\u001B[39;00m \u001B[38;5;28;01mimport\u001B[39;00m Errors\n\u001B[1;32m----> 6\u001B[0m \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01mtokens\u001B[39;00m \u001B[38;5;28;01mimport\u001B[39;00m Doc, Span, Token\n\u001B[0;32m 7\u001B[0m \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01mutil\u001B[39;00m \u001B[38;5;28;01mimport\u001B[39;00m dot_to_dict\n\u001B[0;32m 9\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m TYPE_CHECKING:\n\u001B[0;32m 10\u001B[0m \u001B[38;5;66;03m# This lets us add type hints for mypy etc. without causing circular imports\u001B[39;00m\n",
"how\n", "File \u001B[1;32mj:\\.AppData\\Python\\Python310\\site-packages\\spacy\\tokens\\__init__.py:1\u001B[0m\n\u001B[1;32m----> 1\u001B[0m \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01m_serialize\u001B[39;00m \u001B[38;5;28;01mimport\u001B[39;00m DocBin\n\u001B[0;32m 2\u001B[0m \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01mdoc\u001B[39;00m \u001B[38;5;28;01mimport\u001B[39;00m Doc\n\u001B[0;32m 3\u001B[0m \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01mmorphanalysis\u001B[39;00m \u001B[38;5;28;01mimport\u001B[39;00m MorphAnalysis\n",
"to\n", "File \u001B[1;32mj:\\.AppData\\Python\\Python310\\site-packages\\spacy\\tokens\\_serialize.py:14\u001B[0m\n\u001B[0;32m 12\u001B[0m \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01merrors\u001B[39;00m \u001B[38;5;28;01mimport\u001B[39;00m Errors\n\u001B[0;32m 13\u001B[0m \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01mutil\u001B[39;00m \u001B[38;5;28;01mimport\u001B[39;00m SimpleFrozenList, ensure_path\n\u001B[1;32m---> 14\u001B[0m \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01mvocab\u001B[39;00m \u001B[38;5;28;01mimport\u001B[39;00m Vocab\n\u001B[0;32m 15\u001B[0m \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01m_dict_proxies\u001B[39;00m \u001B[38;5;28;01mimport\u001B[39;00m SpanGroups\n\u001B[0;32m 16\u001B[0m \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01mdoc\u001B[39;00m \u001B[38;5;28;01mimport\u001B[39;00m DOCBIN_ALL_ATTRS \u001B[38;5;28;01mas\u001B[39;00m ALL_ATTRS\n",
"compile\n", "File \u001B[1;32mj:\\.AppData\\Python\\Python310\\site-packages\\spacy\\vocab.pyx:1\u001B[0m, in \u001B[0;36minit spacy.vocab\u001B[1;34m()\u001B[0m\n",
"and\n", "File \u001B[1;32mj:\\.AppData\\Python\\Python310\\site-packages\\spacy\\tokens\\doc.pyx:1\u001B[0m, in \u001B[0;36minit spacy.tokens.doc\u001B[1;34m()\u001B[0m\n",
"run\n", "File \u001B[1;32m<frozen importlib._bootstrap>:404\u001B[0m, in \u001B[0;36mparent\u001B[1;34m(self)\u001B[0m\n",
"a\n", "\u001B[1;31mKeyboardInterrupt\u001B[0m: "
"swing\n",
"application\n",
"from\n",
"the\n",
"command\n",
"line\n",
".\n",
"for\n",
"information\n",
"on\n",
"compile\n",
"and\n",
"run\n",
"a\n",
"swing\n",
"application\n",
"use\n",
"NetBeans\n",
"IDE\n",
",\n",
"see\n",
"Running\n",
"Tutorial\n",
"Examples\n",
"in\n",
"NetBeans\n",
"IDE\n",
".\n",
"the\n",
"compilation\n",
"instruction\n",
"work\n",
"for\n",
"all\n",
"swing\n",
"program\n",
"—\n",
"applet\n",
",\n",
"as\n",
"well\n",
"as\n",
"application\n",
".\n",
"here\n",
"be\n",
"the\n",
"step\n",
"-PRON-\n",
"need\n",
"to\n",
"follow\n",
":\n",
"install\n",
"the\n",
"late\n",
"release\n",
"of\n",
"the\n",
"Java\n",
"SE\n",
"platform\n",
",\n",
"if\n",
"-PRON-\n",
"have\n",
"not\n",
"already\n",
"do\n",
"so\n",
".\n",
"create\n",
"a\n",
"program\n",
"that\n",
"use\n",
"Swing\n",
"component\n",
".\n",
"compile\n",
"the\n",
"program\n",
".\n",
"run\n",
"the\n",
"program\n",
".\n"
] ]
} }
], ],
@ -308,7 +236,12 @@
"outputs": [], "outputs": [],
"source": [ "source": [
"def terminology_lookup():\n", "def terminology_lookup():\n",
" return []" " result = []\n",
" for token in doc:\n",
" if token.lemma_ in dictionary:\n",
" result.append((token, token.idx, token.idx + len(token)))\n",
"\n",
" return result"
] ]
}, },
{ {
@ -343,7 +276,13 @@
"outputs": [], "outputs": [],
"source": [ "source": [
"def get_nouns(text):\n", "def get_nouns(text):\n",
" return []" " result = []\n",
" doc = nlp(text)\n",
" for token in doc:\n",
" if token.pos_ == 'NOUN':\n",
" result.append(token)\n",
"\n",
" return result"
] ]
}, },
{ {
@ -380,7 +319,16 @@
"outputs": [], "outputs": [],
"source": [ "source": [
"def extract_terms(text):\n", "def extract_terms(text):\n",
" return []" " result = {}\n",
" doc = nlp(text)\n",
" for token in doc:\n",
" if token.pos_ == 'NOUN':\n",
" if result.get(token.lemma_) is None:\n",
" result[token.lemma_] = 1\n",
" else:\n",
" result[token.lemma_] += 1\n",
"\n",
" return result"
] ]
}, },
{ {
@ -399,7 +347,16 @@
"outputs": [], "outputs": [],
"source": [ "source": [
"def extract_terms(text):\n", "def extract_terms(text):\n",
" return []" " result = {}\n",
" doc = nlp(text)\n",
" for token in doc:\n",
" if token.pos_ in ['NOUN', 'VERB', 'ADJ']:\n",
" if result.get(token.lemma_) is None:\n",
" result[token.lemma_] = 1\n",
" else:\n",
" result[token.lemma_] += 1\n",
"\n",
" return result"
] ]
} }
], ],
@ -407,7 +364,7 @@
"author": "Rafał Jaworski", "author": "Rafał Jaworski",
"email": "rjawor@amu.edu.pl", "email": "rjawor@amu.edu.pl",
"kernelspec": { "kernelspec": {
"display_name": "Python 3", "display_name": "Python 3 (ipykernel)",
"language": "python", "language": "python",
"name": "python3" "name": "python3"
}, },
@ -422,7 +379,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.8.10" "version": "3.9.2"
}, },
"subtitle": "3. Terminologia", "subtitle": "3. Terminologia",
"title": "Komputerowe wspomaganie tłumaczenia", "title": "Komputerowe wspomaganie tłumaczenia",

130
lab/lab_04-05.ipynb
View File

File diff suppressed because one or more lines are too long

54
lab/lab_06-07.ipynb
View File

@ -60,8 +60,14 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"import regex\n",
"\n",
"\n",
"def find_tags(text):\n", "def find_tags(text):\n",
" return []" " result = []\n",
" for occurance in regex.finditer(\"(\\</?\\w+\\>)\", text, regex.IGNORECASE):\n",
" result.append(occurance.span())\n",
" return result"
] ]
}, },
{ {
@ -79,8 +85,12 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"import regex\n",
"\n",
"\n",
"# Assuming text is a single word\n",
"def is_translatable(text):\n", "def is_translatable(text):\n",
" return True" " return regex.fullmatch(\"[A-Z\\-]+\", text, regex.IGNORECASE) is not None"
] ]
}, },
{ {
@ -98,8 +108,26 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"import regex\n",
"\n",
"\n",
"def find_dates(text):\n", "def find_dates(text):\n",
" return []" " regex_format = regex.compile(\"(?P<day>[0-9]{1,2})[/.-](?P<month>[0-9]{1,2})[/.-](?P<year>[0-9]{4})\")\n",
" matches = regex.match(regex_format, text)\n",
" result = {\n",
" 'day': int(matches.group('day')),\n",
" 'month': int(matches.group('month')),\n",
" 'year': int(matches.group('year')),\n",
" }\n",
"\n",
" return result\n",
"\n",
"\n",
"print(find_dates(\"01/02/1970\"))\n",
"print(find_dates(\"01.02.1970\"))\n",
"print(find_dates(\"01-02-1970\"))\n",
"print(find_dates(\"1/2/1970\"))\n",
"print(find_dates(\"1.2.1970\"))"
] ]
}, },
{ {
@ -130,8 +158,22 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"formats = {\n",
" 'd/m/y': lambda date: f\"{date['day']}/{date['month']}/{date['year']}\",\n",
" 'y-m-d': lambda date: f\"{date['year']}-{date['month']}-{date['day']}\",\n",
"}\n",
"\n",
"\n",
"def correct_dates(source_segment, target_segment, date_format):\n", "def correct_dates(source_segment, target_segment, date_format):\n",
" return ''" " source_date = find_dates(source_segment)\n",
" target_date = find_dates(target_segment)\n",
" if target_date != source_date:\n",
" print('Dates differ')\n",
"\n",
" return formats[date_format](source_date)\n",
"\n",
"\n",
"print(correct_dates(\"1.2.1970\", \"1.2.1970\", 'y-m-d'))"
] ]
}, },
{ {
@ -190,7 +232,7 @@
"author": "Rafał Jaworski", "author": "Rafał Jaworski",
"email": "rjawor@amu.edu.pl", "email": "rjawor@amu.edu.pl",
"kernelspec": { "kernelspec": {
"display_name": "Python 3", "display_name": "Python 3 (ipykernel)",
"language": "python", "language": "python",
"name": "python3" "name": "python3"
}, },
@ -205,7 +247,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.8.10" "version": "3.9.2"
}, },
"subtitle": "6,7. Preprocessing i postprocessing", "subtitle": "6,7. Preprocessing i postprocessing",
"title": "Komputerowe wspomaganie tłumaczenia", "title": "Komputerowe wspomaganie tłumaczenia",