s495724/KWT-2024
1
0
Fork 0
forked from bfijalkowski/KWT-2024
Code Pull Requests Activity

Upload files to "lab"

Browse Source
This commit is contained in:
s495724 2024-04-16 13:36:13 +02:00
parent 71ca3b66ed
commit 9a804fe3dd
3 changed files with 328 additions and 65 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

113
lab/lab_01.ipynb
View File

@ -213,13 +213,34 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 7, "execution_count": 13,
"id": "protected-rings", "id": "protected-rings",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"def tm_lookup(sentence):\n", "def tm_lookup(sentence):\n",
" return ''" " return [entry[1].casefold() for entry in translation_memory if entry[0] == sentence]"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "99d75100-0f9d-4586-82ef-ab42180472a2",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['press the enter button', 'press the enter key']"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tm_lookup('Wciśnij przycisk Enter')"
] ]
}, },
{ {
@ -232,17 +253,17 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 18, "execution_count": 15,
"id": "severe-alloy", "id": "severe-alloy",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"data": { "data": {
"text/plain": [ "text/plain": [
"''" "[]"
] ]
}, },
"execution_count": 18, "execution_count": 15,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -261,13 +282,17 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 11, "execution_count": 16,
"id": "structural-diesel", "id": "structural-diesel",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"import string \n",
"\n",
"def tm_lookup(sentence):\n", "def tm_lookup(sentence):\n",
" return ''" " return [entry[1].casefold() for entry in translation_memory if entry[0] == sentence]\n",
" translator = str.maketrans('', '', string.punctuation) \n",
" return sentence.translate(translator)"
] ]
}, },
{ {
@ -280,17 +305,17 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 12, "execution_count": 20,
"id": "brief-senegal", "id": "brief-senegal",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"data": { "data": {
"text/plain": [ "text/plain": [
"''" "[]"
] ]
}, },
"execution_count": 12, "execution_count": 20,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -317,15 +342,41 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 14, "execution_count": 24,
"id": "mathematical-customs", "id": "mathematical-customs",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"def tm_lookup(sentence):\n", "def tm_lookup(sentence):\n",
" translator = str.maketrans('', '', string.punctuation)\n",
" sentence = sentence.translate(translator).casefold()\n",
" for entry in translation_memory:\n",
" if any(word in entry[0].casefold() for word in sentence.split()):\n",
" return entry[1]\n",
" return ''" " return ''"
] ]
}, },
{
"cell_type": "code",
"execution_count": 25,
"id": "f6537825-62a6-4503-91a5-bbb17d84170b",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'System restart required'"
]
},
"execution_count": 25,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tm_lookup('Wymagane ponowne uruchomienie maszyny')"
]
},
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "meaningful-virus", "id": "meaningful-virus",
@ -344,7 +395,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 15, "execution_count": 26,
"id": "humanitarian-wrong", "id": "humanitarian-wrong",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -362,7 +413,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 16, "execution_count": 27,
"id": "located-perception", "id": "located-perception",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -374,7 +425,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 17, "execution_count": 28,
"id": "advised-casting", "id": "advised-casting",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -384,7 +435,7 @@
"[('przycisk', 'button'), ('drukarka', 'printer')]" "[('przycisk', 'button'), ('drukarka', 'printer')]"
] ]
}, },
"execution_count": 17, "execution_count": 28,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -419,13 +470,35 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 19, "execution_count": 37,
"id": "original-tunisia", "id": "original-tunisia",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"def glossary_lookup(sentence):\n", "def glossary_lookup(sentence):\n",
" return ''" " sentence_words = sentence.casefold().split()\n",
" return [entry for entry in glossary if entry[0] in sentence_words]"
]
},
{
"cell_type": "code",
"execution_count": 39,
"id": "b3ae5504-4168-4fe0-ad25-60558242a31d",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[('przycisk', 'button'), ('drukarka', 'printer')]"
]
},
"execution_count": 39,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"glossary_lookup('Każda Drukarka posiada przycisk wznowienia drukowania')"
] ]
}, },
{ {
@ -438,7 +511,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 20, "execution_count": 38,
"id": "adolescent-semiconductor", "id": "adolescent-semiconductor",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -452,7 +525,7 @@
"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"
}, },
@ -467,7 +540,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.8.10" "version": "3.10.12"
}, },
"subtitle": "1. Podstawowe techniki wspomagania tłumaczenia", "subtitle": "1. Podstawowe techniki wspomagania tłumaczenia",
"title": "Komputerowe wspomaganie tłumaczenia", "title": "Komputerowe wspomaganie tłumaczenia",

112
lab/lab_02.ipynb
View File

@ -57,7 +57,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 1, "execution_count": 31,
"id": "confident-prison", "id": "confident-prison",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -80,13 +80,49 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 2, "execution_count": 29,
"id": "continental-submission", "id": "continental-submission",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"def ice_lookup(sentence, prev_sentence, next_sentence):\n", "def ice_lookup(sentence, prev_sentence, next_sentence, translation_memory):\n",
" return []" " \n",
" ice_previous = \"\"\n",
" ice_next = \"\"\n",
" \n",
" for original, translation in translation_memory:\n",
" if sentence == original:\n",
" index = translation_memory.index((original, translation))\n",
" if index > 0:\n",
" ice_previous = translation_memory[index - 1][1]\n",
" if index < len(translation_memory) - 1:\n",
" ice_next = translation_memory[index + 1][1]\n",
" break\n",
" \n",
" return (ice_previous, ice_next)"
]
},
{
"cell_type": "code",
"execution_count": 35,
"id": "f125ddd2-89fc-4496-93d9-9d640b7f616e",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"prev: Press the ENTER button , next: The printer is switched off\n"
]
}
],
"source": [
"sentence = \"Sprawdź ustawienia sieciowe\"\n",
"prev_sentence = \"Wciśnij przycisk Enter\"\n",
"next_sentence = \"Wymagane ponowne uruchomienie komputera\"\n",
"\n",
"ice_result = ice_lookup(sentence, prev_sentence, next_sentence, translation_memory)\n",
"print('prev: ', ice_result[0], ', next: ', ice_result[1])"
] ]
}, },
{ {
@ -119,7 +155,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 3, "execution_count": 36,
"id": "fourth-pillow", "id": "fourth-pillow",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -141,7 +177,7 @@
"id": "graduate-theorem", "id": "graduate-theorem",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Odpowiedź:" "Odpowiedź: Funkcja nie jest dobrą funkcją dystansu, gdyż bierze pod uwagaę jedynie różnice w długości zdań."
] ]
}, },
{ {
@ -154,7 +190,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 4, "execution_count": 56,
"id": "continued-christopher", "id": "continued-christopher",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -179,7 +215,7 @@
"id": "metallic-leave", "id": "metallic-leave",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Odpowiedź:" "Odpowiedź: Nie jest to dobra funkcja dystansu, gdyż znajduje jedynie fakt, że zdania się mogą między sobą różnić."
] ]
}, },
{ {
@ -206,7 +242,7 @@
"id": "bibliographic-stopping", "id": "bibliographic-stopping",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Odpowiedź:" "Odpowiedź: Dystans Lavenshteina jest poprawną funkcją dystansu, opisuje ilość operacji, które należy wykonać, aby porównywane do siebie zdania były takie same (np. zamiana liter, wstawienie innej litery, usunięcie litery, itp)"
] ]
}, },
{ {
@ -223,7 +259,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 5, "execution_count": 62,
"id": "secondary-wrist", "id": "secondary-wrist",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -233,7 +269,7 @@
"2" "2"
] ]
}, },
"execution_count": 5, "execution_count": 62,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -254,7 +290,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 6, "execution_count": 63,
"id": "associate-tuner", "id": "associate-tuner",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -273,7 +309,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 7, "execution_count": 64,
"id": "focal-pathology", "id": "focal-pathology",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -283,7 +319,7 @@
"0.9166666666666666" "0.9166666666666666"
] ]
}, },
"execution_count": 7, "execution_count": 64,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -294,7 +330,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 8, "execution_count": 65,
"id": "roman-ceiling", "id": "roman-ceiling",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -304,7 +340,7 @@
"0.9428571428571428" "0.9428571428571428"
] ]
}, },
"execution_count": 8, "execution_count": 65,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -315,7 +351,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 9, "execution_count": 66,
"id": "invisible-cambodia", "id": "invisible-cambodia",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -325,7 +361,7 @@
"0.631578947368421" "0.631578947368421"
] ]
}, },
"execution_count": 9, "execution_count": 66,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -344,13 +380,43 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 10, "execution_count": 71,
"id": "genetic-cradle", "id": "genetic-cradle",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"def fuzzy_lookup(sentence, threshold):\n", "import difflib\n",
" return []" "\n",
"def fuzzy_lookup(sentence, threshold, translation_memory):\n",
" fuzzy_matches = []\n",
" for original, translation in translation_memory:\n",
" similarity = difflib.SequenceMatcher(None, sentence, original).ratio()\n",
" if similarity >= threshold:\n",
" fuzzy_matches.append((original, translation, similarity))\n",
" return fuzzy_matches"
]
},
{
"cell_type": "code",
"execution_count": 80,
"id": "6bebcb12-8c73-4beb-b4c2-00553d3b375f",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[('Wciśnij przycisk Enter', 'Press the ENTER button', 0.8636363636363636)]"
]
},
"execution_count": 80,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"sentence = 'Wcisnij pszycisk ęnter'\n",
"threshold = 0.8\n",
"fuzzy_lookup(sentence, threshold, translation_memory)"
] ]
} }
], ],
@ -358,7 +424,7 @@
"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 +439,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.8.10" "version": "3.10.12"
}, },
"subtitle": "2. Zaawansowane użycie pamięci tłumaczeń", "subtitle": "2. Zaawansowane użycie pamięci tłumaczeń",
"title": "Komputerowe wspomaganie tłumaczenia", "title": "Komputerowe wspomaganie tłumaczenia",

168
lab/lab_03.ipynb
View File

@ -63,7 +63,7 @@
"id": "diverse-sunglasses", "id": "diverse-sunglasses",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Odpowiedź:" "Odpowiedź: metal cabinets guides. Proz.com"
] ]
}, },
{ {
@ -128,13 +128,41 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 3, "execution_count": 7,
"id": "cognitive-cedar", "id": "cognitive-cedar",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"def terminology_lookup():\n", "import re\n",
" return []" "\n",
"def terminology_lookup(text, dictionary):\n",
" pattern = re.compile(r'\\b(?:' + '|'.join(dictionary) + r')\\b', re.IGNORECASE)\n",
" matches = pattern.finditer(text)\n",
" occurance = ''\n",
" for match in matches:\n",
" occurance += (f\"({match.start()}, {match.end()})\")\n",
" return occurance"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "5781b95b-3af9-4c82-8388-b98a11e6c343",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'(80, 91)(164, 175)(468, 475)(516, 523)(533, 540)'"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"terminology_lookup(text, dictionary)"
] ]
}, },
{ {
@ -161,7 +189,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 4, "execution_count": 12,
"id": "tribal-attention", "id": "tribal-attention",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -205,7 +233,7 @@
"IDE\n", "IDE\n",
",\n", ",\n",
"see\n", "see\n",
"Running\n", "run\n",
"Tutorial\n", "Tutorial\n",
"Examples\n", "Examples\n",
"in\n", "in\n",
@ -218,7 +246,7 @@
"work\n", "work\n",
"for\n", "for\n",
"all\n", "all\n",
"swing\n", "Swing\n",
"program\n", "program\n",
"—\n", "—\n",
"applet\n", "applet\n",
@ -232,7 +260,7 @@
"be\n", "be\n",
"the\n", "the\n",
"step\n", "step\n",
"-PRON-\n", "you\n",
"need\n", "need\n",
"to\n", "to\n",
"follow\n", "follow\n",
@ -248,7 +276,7 @@
"platform\n", "platform\n",
",\n", ",\n",
"if\n", "if\n",
"-PRON-\n", "you\n",
"have\n", "have\n",
"not\n", "not\n",
"already\n", "already\n",
@ -260,7 +288,7 @@
"program\n", "program\n",
"that\n", "that\n",
"use\n", "use\n",
"Swing\n", "swing\n",
"component\n", "component\n",
".\n", ".\n",
"compile\n", "compile\n",
@ -302,13 +330,31 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 5, "execution_count": 19,
"id": "surgical-demonstration", "id": "surgical-demonstration",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"def terminology_lookup():\n", "def terminology_lookup(text, dictionary):\n",
" return []" " nlp = spacy.load(\"en_core_web_sm\")\n",
" doc = nlp(text)\n",
"\n",
" word_forms = set()\n",
" for word in dictionary:\n",
" word_forms.add(word)\n",
" for token in doc:\n",
" if token.text.lower() == word:\n",
" word_forms.add(token.lemma_)\n",
"\n",
" matches = []\n",
" for token in doc:\n",
" if token.text.lower() in word_forms:\n",
" matches.append((token.idx, token.idx + len(token)))\n",
"\n",
" occurrences = ''\n",
" for match in matches:\n",
" occurrences += f\"({match[0]}, {match[1]})\"\n",
" return occurrences"
] ]
}, },
{ {
@ -337,13 +383,59 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 6, "execution_count": 23,
"id": "superb-butterfly", "id": "superb-butterfly",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"def get_nouns(text):\n", "def get_nouns(text):\n",
" return []" " nlp = spacy.load(\"en_core_web_sm\")\n",
" doc = nlp(text)\n",
" nouns = [token.text for token in doc if token.pos_ == \"NOUN\"]\n",
" \n",
" return nouns"
]
},
{
"cell_type": "code",
"execution_count": 24,
"id": "8203c3e5-74a6-42c1-add1-e378f09164fd",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['programmers',\n",
" 'section',\n",
" 'Swing',\n",
" 'application',\n",
" 'command',\n",
" 'line',\n",
" 'information',\n",
" 'Swing',\n",
" 'application',\n",
" 'compilation',\n",
" 'instructions',\n",
" 'programs',\n",
" 'applets',\n",
" 'applications',\n",
" 'steps',\n",
" 'release',\n",
" 'platform',\n",
" 'program',\n",
" 'Swing',\n",
" 'components',\n",
" 'program',\n",
" 'program']"
]
},
"execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"get_nouns(text)"
] ]
}, },
{ {
@ -356,7 +448,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 7, "execution_count": 25,
"id": "acting-tolerance", "id": "acting-tolerance",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -374,13 +466,29 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 8, "execution_count": 30,
"id": "eight-redhead", "id": "eight-redhead",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"def extract_terms(text):\n", "def extract_terms(text):\n",
" return []" " nlp = spacy.load(\"en_core_web_sm\")\n",
" doc = nlp(text)\n",
" \n",
" tally = {}\n",
" \n",
" for token in doc:\n",
" if token.pos_ != \"NOUN\":\n",
" continue\n",
" \n",
" lemma = token.lemma_.lower()\n",
" \n",
" if lemma in tally:\n",
" tally[lemma] += 1\n",
" else:\n",
" tally[lemma] = 1\n",
" \n",
" return tally"
] ]
}, },
{ {
@ -393,13 +501,29 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 9, "execution_count": 32,
"id": "monetary-mambo", "id": "monetary-mambo",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"def extract_terms(text):\n", "def extract_terms(text):\n",
" return []" " nlp = spacy.load(\"en_core_web_sm\")\n",
" doc = nlp(text)\n",
" \n",
" tally = {}\n",
" \n",
" for token in doc:\n",
" if token.pos_ not in ['NOUN', 'VERB', 'ADJ']:\n",
" continue\n",
" \n",
" lemma = token.lemma_.lower()\n",
" \n",
" if lemma in tally:\n",
" tally[lemma] += 1\n",
" else:\n",
" tally[lemma] = 1\n",
" \n",
" return tally"
] ]
} }
], ],
@ -407,7 +531,7 @@
"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 +546,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.8.10" "version": "3.10.12"
}, },
"subtitle": "3. Terminologia", "subtitle": "3. Terminologia",
"title": "Komputerowe wspomaganie tłumaczenia", "title": "Komputerowe wspomaganie tłumaczenia",