s351820/KWT-2024
1
0
Fork 0
forked from bfijalkowski/KWT-2024
Code Pull Requests Activity

Compare commits

base: s351820:main
Branches Tags
s351820:main
bfijalkowski:main
..
compare: bfijalkowski:main
Branches Tags
bfijalkowski:main
s351820:main

No commits in common. "main" and "main" have entirely different histories.
main ... main

9 changed files with 67 additions and 2338 deletions
Show Stats Expand all files Collapse all files

132
lab/lab_01.ipynb
View File

@ -251,40 +251,10 @@
"tm_lookup('Wciśnij przycisk [ENTER]')" "tm_lookup('Wciśnij przycisk [ENTER]')"
] ]
}, },
{
"cell_type": "code",
"execution_count": 1,
"id": "36510584-d363-444d-bfdb-2f0260d197cd",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['Press the ENTER button']"
]
},
"execution_count": 1,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"translation_memory = [('Wciśnij przycisk Enter', 'Press the ENTER button'), \n",
" ('Sprawdź ustawienia sieciowe', 'Check the network settings')]\n",
"\n",
"def tm_lookup(sentence):\n",
" return [entry[1] for entry in translation_memory if entry[0].lower() == sentence.lower()]\n",
"\n",
"#tm_lookup('Wciśnij przycisk Enter') # -> ['Press the ENTER button'] OK\n",
"tm_lookup('Wciśnij przycisk ENTER') # -> ['Press the ENTER button'] OK"
]
},
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "choice-committee", "id": "choice-committee",
"metadata": { "metadata": {},
"tags": []
},
"source": [ "source": [
"### Ćwiczenie 2: zmodyfikuj funkcję tm_lookup w taki sposób, aby nie brała pod uwagę znaków interpunkcyjnych. Rada - zdefiniuj funkcję sentence_similar." "### Ćwiczenie 2: zmodyfikuj funkcję tm_lookup w taki sposób, aby nie brała pod uwagę znaków interpunkcyjnych. Rada - zdefiniuj funkcję sentence_similar."
] ]
@ -329,66 +299,6 @@
"tm_lookup('Wymagane ponowne uruchomienie maszyny')" "tm_lookup('Wymagane ponowne uruchomienie maszyny')"
] ]
}, },
{
"cell_type": "code",
"execution_count": 24,
"id": "25af95de-30e0-468c-8c0c-2478ce0d8856",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"wciśnijprzyciskenter\n",
"wciśnijprzyciskenter\n"
]
},
{
"data": {
"text/plain": [
"'Press the ENTER button'"
]
},
"execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import re\n",
"translation_memory = [('Wciśnij przycisk Enter', 'Press the ENTER button'), \n",
" ('Sprawdź ustawienia sieciowe', 'Check the network settings')]\n",
"\n",
"def sentence_cleanup(sentence):\n",
" x = sentence.replace(\" \", \"\")\n",
" x = x.replace(\"\\s\", \"\")\n",
" x = x.replace(\"\\t\", \"\")\n",
" x = x.replace(\"\\v\", \"\")\n",
" x = x.replace(\"\\n\", \"\")\n",
" x = x.replace(\"\\r\", \"\")\n",
" x = x.replace(\"\\f\", \"\")\n",
" x = x.replace(\".\", \"\")\n",
" x = x.replace(\"!\", \"\")\n",
" x = x.replace(\":\", \"\")\n",
" x = x.replace('?', \"\")\n",
" x = x.replace(\";\", \"\")\n",
" x = x.replace('\"', \"\")\n",
" x = x.lower()\n",
" print(x)\n",
" return x\n",
"\n",
"def tm_lookup(sentence):\n",
" for entry in translation_memory:\n",
" part1 = entry[0]\n",
" part2 = entry[1]\n",
" better_sentence = sentence_cleanup(sentence)\n",
" better_entry = sentence_cleanup(part1)\n",
" if better_entry == better_sentence:\n",
" return part2\n",
"\n",
"tm_lookup('Wciśnij przycisk:ENTER!') # -> ['Press the ENTER button'] OK"
]
},
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "guided-tutorial", "id": "guided-tutorial",
@ -499,34 +409,6 @@
"Odpowiedź:" "Odpowiedź:"
] ]
}, },
{
"cell_type": "code",
"execution_count": 31,
"id": "6347bc85-194d-45c4-a30d-5e5e06033821",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[('przycisk', 'button'), ('drukarka', 'printer')]"
]
},
"execution_count": 31,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"glossary = [('komputer', 'computer'), ('przycisk', 'button'), ('drukarka', 'printer')]\n",
"\n",
"def glossary_lookup(sentence):\n",
" better_sentence = sentence.lower()\n",
" sentence_words = better_sentence.split()\n",
" return [entry for entry in glossary if entry[0] in sentence_words]\n",
"\n",
"glossary_lookup('Każda DRUKARKA posiada PrzycisK wznowienia drukowania')"
]
},
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "objective-matthew", "id": "objective-matthew",
@ -542,14 +424,8 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"glossary = [('komputer', 'computer'), ('przycisk', 'button'), ('drukarka', 'printer')]\n",
"\n",
"def glossary_lookup(sentence):\n", "def glossary_lookup(sentence):\n",
" better_sentence = sentence.lower()\n", " return ''"
" sentence_words = better_sentence.split()\n",
" return [entry for entry in glossary if entry[0] in sentence_words]\n",
"\n",
"glossary_lookup('Każda DRUKARKA posiada PrzycisK wznowienia drukowania')"
] ]
}, },
{ {
@ -576,7 +452,7 @@
"author": "Rafał Jaworski", "author": "Rafał Jaworski",
"email": "rjawor@amu.edu.pl", "email": "rjawor@amu.edu.pl",
"kernelspec": { "kernelspec": {
"display_name": "Python 3 (ipykernel)", "display_name": "Python 3",
"language": "python", "language": "python",
"name": "python3" "name": "python3"
}, },
@ -591,7 +467,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.9.2" "version": "3.8.10"
}, },
"subtitle": "1. Podstawowe techniki wspomagania tłumaczenia", "subtitle": "1. Podstawowe techniki wspomagania tłumaczenia",
"title": "Komputerowe wspomaganie tłumaczenia", "title": "Komputerowe wspomaganie tłumaczenia",

65
lab/lab_02.ipynb
View File

@ -223,17 +223,17 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 7, "execution_count": 5,
"id": "secondary-wrist", "id": "secondary-wrist",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"data": { "data": {
"text/plain": [ "text/plain": [
"3" "2"
] ]
}, },
"execution_count": 8, "execution_count": 5,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -344,70 +344,21 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 19, "execution_count": 10,
"id": "genetic-cradle", "id": "genetic-cradle",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [],
{
"name": "stdout",
"output_type": "stream",
"text": [
"Wciśnij przycisk Enter -> Wciśnij przycisk Enter [ SCORE = 1.0 ]\n",
"Wciśnij przycisk Enter -> Wciśnij przycisk ENTER [ SCORE = 0.8181818181818181 ]\n",
"Wciśnij przycisk Enter -> Wciśnij przycisk Enter! [ SCORE = 0.9565217391304348 ]\n"
]
}
],
"source": [ "source": [
"#!pip3 install python-Levenshtein\n",
"from Levenshtein import distance as levenshtein_distance\n",
"\n",
"translation_memory = [\n",
" ('Wciśnij przycisk Enter', 'Press the ENTER button'),\n",
" ('Wciśnij przycisk ENTER', 'Press the ENTER button'), \n",
" ('Wciśnij przycisk Enter!', 'Press the ENTER button!'), \n",
" ('Wciśnij przycisk', 'Press the button'), \n",
" ('Wciśnij Enter', 'Press the ENTER'), \n",
" ('Sprawdź ustawienia sieciowe', 'Check the network settings'),\n",
" ('Drukarka jest wyłączona', 'The printer is switched off'),\n",
" ('Wymagane ponowne uruchomienie komputera', 'System restart required')\n",
" ]\n",
"\n",
"def levenshtein_similarity(x,y):\n",
" return 1 - levenshtein_distance(x,y) / max(len(x), len(y))\n",
"\n",
"def fuzzy_lookup(sentence, threshold):\n", "def fuzzy_lookup(sentence, threshold):\n",
" for entry in translation_memory:\n", " return []"
" part1 = entry[0]\n",
" score = levenshtein_similarity(sentence, part1)\n",
" if score >= threshold:\n",
" print(sentence + ' -> ' + part1 + ' [ SCORE = ' + str(score) + ' ]')\n",
"\n",
"fuzzy_lookup('Wciśnij przycisk Enter', 0.8)"
] ]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8b7bb6aa-5aaf-4f49-84ab-edbe6797d568",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "3b095fff-71a8-44a9-b809-d872ee9a7b62",
"metadata": {},
"outputs": [],
"source": []
} }
], ],
"metadata": { "metadata": {
"author": "Rafał Jaworski", "author": "Rafał Jaworski",
"email": "rjawor@amu.edu.pl", "email": "rjawor@amu.edu.pl",
"kernelspec": { "kernelspec": {
"display_name": "Python 3 (ipykernel)", "display_name": "Python 3",
"language": "python", "language": "python",
"name": "python3" "name": "python3"
}, },
@ -422,7 +373,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.9.2" "version": "3.8.10"
}, },
"subtitle": "2. Zaawansowane użycie pamięci tłumaczeń", "subtitle": "2. Zaawansowane użycie pamięci tłumaczeń",
"title": "Komputerowe wspomaganie tłumaczenia", "title": "Komputerowe wspomaganie tłumaczenia",

56
lab/lab_03.ipynb
View File

@ -63,14 +63,7 @@
"id": "diverse-sunglasses", "id": "diverse-sunglasses",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Odpowiedź:\n", "Odpowiedź:"
"\n",
"slides of metal cabinet\n",
"\n",
"Źródła - tłumaczono z PL -> ENG oraz ENG -> PL\n",
"https://translate.google.pl/?hl=pl&sl=en&tl=pl&text=metal%20cabinet%20slides&op=translate\n",
"\n",
"https://www.deepl.com/pl/translator#en/pl/slides%20of%20metal%20cabinet"
] ]
}, },
{ {
@ -135,50 +128,13 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 97, "execution_count": 3,
"id": "cognitive-cedar", "id": "cognitive-cedar",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [],
{
"name": "stdout",
"output_type": "stream",
"text": [
"program(14, 21)\n",
"program(291, 298)\n",
"program(468, 475)\n",
"program(516, 523)\n",
"program(533, 540)\n",
"application(80, 91)\n",
"application(164, 175)\n",
"application(322, 333)\n",
"applet(302, 308)\n",
"compile(56, 63)\n"
]
}
],
"source": [ "source": [
"import re\n",
"\n",
"text = \" For all Java programmers:\"\n",
"text += \" This section explains how to compile and run a Swing application from the command line.\"\n",
"text += \" For information on compiling and running a Swing application using NetBeans IDE,\"\n",
"text += \" see Running Tutorial Examples in NetBeans IDE. The compilation instructions work for all Swing programs\"\n",
"text += \" — applets, as well as applications. Here are the steps you need to follow:\"\n",
"text += \" Install the latest release of the Java SE platform, if you haven't already done so.\"\n",
"text += \" Create a program that uses Swing components. Compile the program. Run the program.\"\n",
"\n",
"dictionary = ['program', 'application', 'applet', 'compile']\n",
"\n",
"def terminology_lookup():\n", "def terminology_lookup():\n",
" for entry in dictionary:\n", " return []"
" p = r\"\\b\" + entry + \"\\w+\" \n",
" p1 = r\"\\b\" + entry\n",
" re_pattern = re.compile(p1)\n",
" match = re_pattern.finditer(text)\n",
" for x in match:\n",
" print(entry + str(x.span()))\n",
" \n",
"terminology_lookup()"
] ]
}, },
{ {
@ -451,7 +407,7 @@
"author": "Rafał Jaworski", "author": "Rafał Jaworski",
"email": "rjawor@amu.edu.pl", "email": "rjawor@amu.edu.pl",
"kernelspec": { "kernelspec": {
"display_name": "Python 3 (ipykernel)", "display_name": "Python 3",
"language": "python", "language": "python",
"name": "python3" "name": "python3"
}, },
@ -466,7 +422,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.9.2" "version": "3.8.10"
}, },
"subtitle": "3. Terminologia", "subtitle": "3. Terminologia",
"title": "Komputerowe wspomaganie tłumaczenia", "title": "Komputerowe wspomaganie tłumaczenia",

71
lab/lab_08.ipynb
View File

@ -57,62 +57,13 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 6, "execution_count": 1,
"id": "moving-clothing", "id": "moving-clothing",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [],
{
"ename": "TypeError",
"evalue": "Fraction.__new__() got an unexpected keyword argument '_normalize'",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mTypeError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[1;32mIn[6], line 35\u001b[0m\n\u001b[0;32m 32\u001b[0m predictions \u001b[38;5;241m=\u001b[39m [\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mthe\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpicture\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mthe\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpicture\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mby\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mme\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n\u001b[0;32m 34\u001b[0m \u001b[38;5;66;03m# Calculate BLEU score with weights\u001b[39;00m\n\u001b[1;32m---> 35\u001b[0m score \u001b[38;5;241m=\u001b[39m \u001b[43msentence_bleu\u001b[49m\u001b[43m(\u001b[49m\u001b[43mreference\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpredictions\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mweights\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mweights\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 36\u001b[0m \u001b[38;5;28mprint\u001b[39m(score)\n",
"File \u001b[1;32m~\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\nltk\\translate\\bleu_score.py:107\u001b[0m, in \u001b[0;36msentence_bleu\u001b[1;34m(references, hypothesis, weights, smoothing_function, auto_reweigh)\u001b[0m\n\u001b[0;32m 20\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21msentence_bleu\u001b[39m(\n\u001b[0;32m 21\u001b[0m references,\n\u001b[0;32m 22\u001b[0m hypothesis,\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 25\u001b[0m auto_reweigh\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m,\n\u001b[0;32m 26\u001b[0m ):\n\u001b[0;32m 27\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m 28\u001b[0m \u001b[38;5;124;03m Calculate BLEU score (Bilingual Evaluation Understudy) from\u001b[39;00m\n\u001b[0;32m 29\u001b[0m \u001b[38;5;124;03m Papineni, Kishore, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002.\u001b[39;00m\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 105\u001b[0m \u001b[38;5;124;03m :rtype: float / list(float)\u001b[39;00m\n\u001b[0;32m 106\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[1;32m--> 107\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mcorpus_bleu\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m 108\u001b[0m \u001b[43m \u001b[49m\u001b[43m[\u001b[49m\u001b[43mreferences\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m[\u001b[49m\u001b[43mhypothesis\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mweights\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43msmoothing_function\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mauto_reweigh\u001b[49m\n\u001b[0;32m 109\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[1;32m~\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\nltk\\translate\\bleu_score.py:210\u001b[0m, in \u001b[0;36mcorpus_bleu\u001b[1;34m(list_of_references, hypotheses, weights, smoothing_function, auto_reweigh)\u001b[0m\n\u001b[0;32m 206\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m references, hypothesis \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mzip\u001b[39m(list_of_references, hypotheses):\n\u001b[0;32m 207\u001b[0m \u001b[38;5;66;03m# For each order of ngram, calculate the numerator and\u001b[39;00m\n\u001b[0;32m 208\u001b[0m \u001b[38;5;66;03m# denominator for the corpus-level modified precision.\u001b[39;00m\n\u001b[0;32m 209\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m i \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mrange\u001b[39m(\u001b[38;5;241m1\u001b[39m, max_weight_length \u001b[38;5;241m+\u001b[39m \u001b[38;5;241m1\u001b[39m):\n\u001b[1;32m--> 210\u001b[0m p_i \u001b[38;5;241m=\u001b[39m \u001b[43mmodified_precision\u001b[49m\u001b[43m(\u001b[49m\u001b[43mreferences\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mhypothesis\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mi\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 211\u001b[0m p_numerators[i] \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m p_i\u001b[38;5;241m.\u001b[39mnumerator\n\u001b[0;32m 212\u001b[0m p_denominators[i] \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m p_i\u001b[38;5;241m.\u001b[39mdenominator\n",
"File \u001b[1;32m~\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\nltk\\translate\\bleu_score.py:368\u001b[0m, in \u001b[0;36mmodified_precision\u001b[1;34m(references, hypothesis, n)\u001b[0m\n\u001b[0;32m 364\u001b[0m \u001b[38;5;66;03m# Ensures that denominator is minimum 1 to avoid ZeroDivisionError.\u001b[39;00m\n\u001b[0;32m 365\u001b[0m \u001b[38;5;66;03m# Usually this happens when the ngram order is > len(reference).\u001b[39;00m\n\u001b[0;32m 366\u001b[0m denominator \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mmax\u001b[39m(\u001b[38;5;241m1\u001b[39m, \u001b[38;5;28msum\u001b[39m(counts\u001b[38;5;241m.\u001b[39mvalues()))\n\u001b[1;32m--> 368\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mFraction\u001b[49m\u001b[43m(\u001b[49m\u001b[43mnumerator\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdenominator\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m_normalize\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m)\u001b[49m\n",
"\u001b[1;31mTypeError\u001b[0m: Fraction.__new__() got an unexpected keyword argument '_normalize'"
]
}
],
"source": [ "source": [
"#!pip install nltk\n", "def calculate_bleu():\n",
"#from nltk.translate.bleu_score import sentence_bleu, corpus_bleu\n", " return 0"
"#import zipfile\n",
"#archive = zipfile.ZipFile('./data/corpus_corrected.zip', 'r')\n",
"#reference1 = archive.read('corpus_the_human.txt')\n",
"#reference2 = archive.read('corpus_the_nmt.txt')\n",
"#translation = archive.read('corpus_en.txt')\n",
"\n",
"# Prepare the reference sentences\n",
"#reference1 = ['I', 'love', 'eating', 'ice', 'cream']\n",
"#reference2 = ['I', 'enjoy', 'eating', 'ice', 'cream']\n",
"#translation = ['I', 'love', 'eating', 'ice', 'cream']\n",
"\n",
"#bleu_score = sentence_bleu([reference1, reference2], translation)\n",
"#print(\"BLEU Score: \", bleu_score)\n",
"# Calculate the BLEU score for a single sentence\n",
"\n",
"#def calculate_bleu(reference1,reference2,translation):\n",
"# bleu_score = sentence_bleu([reference1, reference2], translation)\n",
"# print(\"BLEU Score: \", bleu_score)\n",
"# return bleu_score\n",
"#\n",
"#calculate_bleu(reference1,reference2,translation)\n",
"\n",
"# V2\n",
"from nltk.translate.bleu_score import sentence_bleu, corpus_bleu \n",
"# Define your desired weights (example: higher weight for bi-grams)\n",
"weights = (0.25, 0.25, 0, 0) # Weights for uni-gram, bi-gram, tri-gram, and 4-gram \n",
"# Reference and predicted texts (same as before)\n",
"reference = [[\"the\", \"picture\", \"is\", \"clicked\", \"by\", \"me\"],\n",
" [\"this\", \"picture\", \"was\", \"clicked\", \"by\", \"me\"]]\n",
"predictions = [\"the\", \"picture\", \"the\", \"picture\", \"by\", \"me\"]\n",
" \n",
"# Calculate BLEU score with weights\n",
"score = sentence_bleu(reference, predictions, weights=weights)\n",
"print(score)"
] ]
}, },
{ {
@ -239,12 +190,15 @@
"metadata": { "metadata": {
"author": "Rafał Jaworski", "author": "Rafał Jaworski",
"email": "rjawor@amu.edu.pl", "email": "rjawor@amu.edu.pl",
"lang": "pl",
"subtitle": "8. Wykorzystanie tłumaczenia automatycznego we wspomaganiu tłumaczenia",
"title": "Komputerowe wspomaganie tłumaczenia",
"year": "2021",
"kernelspec": { "kernelspec": {
"display_name": "Python 3 (ipykernel)", "display_name": "Python 3",
"language": "python", "language": "python",
"name": "python3" "name": "python3"
}, },
"lang": "pl",
"language_info": { "language_info": {
"codemirror_mode": { "codemirror_mode": {
"name": "ipython", "name": "ipython",
@ -255,11 +209,8 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.12.2" "version": "3.8.10"
}, }
"subtitle": "8. Wykorzystanie tłumaczenia automatycznego we wspomaganiu tłumaczenia",
"title": "Komputerowe wspomaganie tłumaczenia",
"year": "2021"
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 5 "nbformat_minor": 5

2043
lab/lab_09-10.ipynb
View File

File diff suppressed because one or more lines are too long

14
lab/lab_11.ipynb
View File

@ -187,12 +187,15 @@
"metadata": { "metadata": {
"author": "Rafał Jaworski", "author": "Rafał Jaworski",
"email": "rjawor@amu.edu.pl", "email": "rjawor@amu.edu.pl",
"lang": "pl",
"subtitle": "11. Urównoleglanie",
"title": "Komputerowe wspomaganie tłumaczenia",
"year": "2021",
"kernelspec": { "kernelspec": {
"display_name": "Python 3 (ipykernel)", "display_name": "Python 3",
"language": "python", "language": "python",
"name": "python3" "name": "python3"
}, },
"lang": "pl",
"language_info": { "language_info": {
"codemirror_mode": { "codemirror_mode": {
"name": "ipython", "name": "ipython",
@ -203,11 +206,8 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.12.2" "version": "3.8.10"
}, }
"subtitle": "11. Urównoleglanie",
"title": "Komputerowe wspomaganie tłumaczenia",
"year": "2021"
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 5 "nbformat_minor": 5

14
lab/lab_12.ipynb
View File

@ -154,12 +154,15 @@
"metadata": { "metadata": {
"author": "Rafał Jaworski", "author": "Rafał Jaworski",
"email": "rjawor@amu.edu.pl", "email": "rjawor@amu.edu.pl",
"lang": "pl",
"subtitle": "12. Key logging",
"title": "Komputerowe wspomaganie tłumaczenia",
"year": "2021",
"kernelspec": { "kernelspec": {
"display_name": "Python 3 (ipykernel)", "display_name": "Python 3",
"language": "python", "language": "python",
"name": "python3" "name": "python3"
}, },
"lang": "pl",
"language_info": { "language_info": {
"codemirror_mode": { "codemirror_mode": {
"name": "ipython", "name": "ipython",
@ -170,11 +173,8 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.12.2" "version": "3.8.10"
}, }
"subtitle": "12. Key logging",
"title": "Komputerowe wspomaganie tłumaczenia",
"year": "2021"
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 5 "nbformat_minor": 5

4
lab/lab_13-14.ipynb
View File

@ -201,7 +201,7 @@
"author": "Rafał Jaworski", "author": "Rafał Jaworski",
"email": "rjawor@amu.edu.pl", "email": "rjawor@amu.edu.pl",
"kernelspec": { "kernelspec": {
"display_name": "Python 3 (ipykernel)", "display_name": "Python 3",
"language": "python", "language": "python",
"name": "python3" "name": "python3"
}, },
@ -216,7 +216,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.12.2" "version": "3.8.10"
}, },
"subtitle": "13,14. Korekta pisowni", "subtitle": "13,14. Korekta pisowni",
"title": "Komputerowe wspomaganie tłumaczenia", "title": "Komputerowe wspomaganie tłumaczenia",

4
lab/lab_15.ipynb
View File

@ -155,7 +155,7 @@
"author": "Rafał Jaworski", "author": "Rafał Jaworski",
"email": "rjawor@amu.edu.pl", "email": "rjawor@amu.edu.pl",
"kernelspec": { "kernelspec": {
"display_name": "Python 3 (ipykernel)", "display_name": "Python 3",
"language": "python", "language": "python",
"name": "python3" "name": "python3"
}, },
@ -170,7 +170,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.12.2" "version": "3.8.10"
}, },
"subtitle": "15. Korekta gramatyczna", "subtitle": "15. Korekta gramatyczna",
"title": "Komputerowe wspomaganie tłumaczenia", "title": "Komputerowe wspomaganie tłumaczenia",