s375262
/
KWT-2024
forked from bfijalkowski/KWT-2024
1
0
Fork 0
Code Pull Requests Activity

Laboratoria 13.04.2024

This commit is contained in:
Marek Susniak 2024-04-15 19:34:20 +02:00
parent 71ca3b66ed
commit 957bd22d58
3 changed files with 293 additions and 70 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

162
lab/lab_01.ipynb
View File

@ -52,7 +52,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 1, "execution_count": 77,
"id": "narrow-romantic", "id": "narrow-romantic",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -71,7 +71,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 2, "execution_count": 78,
"id": "indonesian-electron", "id": "indonesian-electron",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -82,7 +82,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 3, "execution_count": 79,
"id": "compact-trinidad", "id": "compact-trinidad",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -92,7 +92,7 @@
"['Press the ENTER button']" "['Press the ENTER button']"
] ]
}, },
"execution_count": 3, "execution_count": 79,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -119,7 +119,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 4, "execution_count": 80,
"id": "exposed-daniel", "id": "exposed-daniel",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -139,7 +139,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 5, "execution_count": 81,
"id": "serial-velvet", "id": "serial-velvet",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -149,7 +149,7 @@
"['Press the ENTER button', 'Press the ENTER key']" "['Press the ENTER button', 'Press the ENTER key']"
] ]
}, },
"execution_count": 5, "execution_count": 81,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -176,7 +176,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 6, "execution_count": 82,
"id": "every-gibson", "id": "every-gibson",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -186,7 +186,7 @@
"[]" "[]"
] ]
}, },
"execution_count": 6, "execution_count": 82,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -213,13 +213,15 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 7, "execution_count": 83,
"id": "protected-rings", "id": "protected-rings",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"def tm_lookup(sentence):\n", "def tm_lookup(sentence):\n",
" return ''" " lowerSentence = sentence.lower()\n",
"\n",
" return [entry[1] for entry in translation_memory if entry[0].lower() == lowerSentence]"
] ]
}, },
{ {
@ -232,17 +234,17 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 18, "execution_count": 84,
"id": "severe-alloy", "id": "60a6c976",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"data": { "data": {
"text/plain": [ "text/plain": [
"''" "[]"
] ]
}, },
"execution_count": 18, "execution_count": 84,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -261,13 +263,21 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 11, "execution_count": 85,
"id": "structural-diesel", "id": "structural-diesel",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"import string\n",
"\n",
"def prepare_sentence(sentence):\n",
" translator = str.maketrans('', '', string.punctuation)\n",
"\n",
" return sentence.lower().translate(translator)\n",
"\n",
"def tm_lookup(sentence):\n", "def tm_lookup(sentence):\n",
" return ''" " lowerSentence = prepare_sentence(sentence)\n",
" return [entry[1] for entry in translation_memory if prepare_sentence(entry[0]) == lowerSentence]"
] ]
}, },
{ {
@ -280,17 +290,17 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 12, "execution_count": 86,
"id": "brief-senegal", "id": "brief-senegal",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"data": { "data": {
"text/plain": [ "text/plain": [
"''" "[]"
] ]
}, },
"execution_count": 12, "execution_count": 86,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -317,13 +327,43 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 14, "execution_count": 87,
"id": "mathematical-customs", "id": "mathematical-customs",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"import string\n",
"\n",
"def prepare_sentence(sentence):\n",
" translator = str.maketrans('', '', string.punctuation)\n",
"\n",
" return sentence.lower().translate(translator)\n",
"\n",
"def sentence_similar(sentence1, sentence2):\n",
" words1 = sentence1.split()\n",
" words2 = sentence2.split()\n",
" \n",
" min_length = min(len(words1), len(words2))\n",
" \n",
" matched_count = 0\n",
" for i in range(min_length):\n",
" if prepare_sentence(words1[i]) == prepare_sentence(words2[i]):\n",
" matched_count += 1\n",
" \n",
" return {\n",
" \"count\": matched_count,\n",
" \"length\": min_length\n",
" }\n",
"\n",
"def tm_lookup(sentence):\n", "def tm_lookup(sentence):\n",
" return ''" " collection = []\n",
"\n",
" for entry in translation_memory:\n",
" similarity = sentence_similar(sentence, entry[0])\n",
" if similarity[\"length\"] - similarity[\"count\"] <= 1:\n",
" collection.append(entry[1])\n",
"\n",
" return collection\n"
] ]
}, },
{ {
@ -344,7 +384,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 15, "execution_count": 88,
"id": "humanitarian-wrong", "id": "humanitarian-wrong",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -362,7 +402,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 16, "execution_count": 89,
"id": "located-perception", "id": "located-perception",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -374,7 +414,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 17, "execution_count": 90,
"id": "advised-casting", "id": "advised-casting",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -384,7 +424,7 @@
"[('przycisk', 'button'), ('drukarka', 'printer')]" "[('przycisk', 'button'), ('drukarka', 'printer')]"
] ]
}, },
"execution_count": 17, "execution_count": 90,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -406,7 +446,7 @@
"id": "defensive-fifteen", "id": "defensive-fifteen",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Odpowiedź:" "Odpowiedź: Jest to n przeszukiwań po liście m-elementowej co daje złozonosc O(n*m)"
] ]
}, },
{ {
@ -419,13 +459,40 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 19, "execution_count": 91,
"id": "original-tunisia", "id": "original-tunisia",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"def prepare_sentence(sentence):\n",
" return sentence.lower()\n",
"\n",
"def glossary_lookup(sentence):\n", "def glossary_lookup(sentence):\n",
" return ''" " sentence_words = sentence.split()\n",
" lowered_words = list(map(prepare_sentence, sentence_words))\n",
"\n",
" return [entry for entry in glossary if prepare_sentence(entry[0]) in lowered_words]"
]
},
{
"cell_type": "code",
"execution_count": 92,
"id": "df948bb3",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[('komputer', 'computer')]"
]
},
"execution_count": 92,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"glossary_lookup(\"Komputer\")"
] ]
}, },
{ {
@ -438,13 +505,44 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 20, "execution_count": 93,
"id": "adolescent-semiconductor", "id": "adolescent-semiconductor",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"def prepare_dictionary(sentences):\n",
" dict = {}\n",
"\n",
" for entry in sentences:\n",
" dict[entry[0].lower()] = entry\n",
"\n",
" return dict\n",
"\n",
"glossary_dict = prepare_dictionary(glossary)\n",
"\n",
"def glossary_lookup(sentence):\n", "def glossary_lookup(sentence):\n",
" return ''" " return glossary_dict[sentence.lower()]"
]
},
{
"cell_type": "code",
"execution_count": 94,
"id": "98e9ff56",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"('komputer', 'computer')"
]
},
"execution_count": 94,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"glossary_lookup(\"Komputer\")"
] ]
} }
], ],
@ -467,7 +565,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.8.10" "version": "3.7.9"
}, },
"subtitle": "1. Podstawowe techniki wspomagania tłumaczenia", "subtitle": "1. Podstawowe techniki wspomagania tłumaczenia",
"title": "Komputerowe wspomaganie tłumaczenia", "title": "Komputerowe wspomaganie tłumaczenia",

131
lab/lab_02.ipynb
View File

@ -57,7 +57,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 1, "execution_count": 92,
"id": "confident-prison", "id": "confident-prison",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -80,15 +80,51 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 2, "execution_count": 93,
"id": "continental-submission", "id": "continental-submission",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"def ice_lookup(sentence, prev_sentence, next_sentence):\n", "def prepare_dictionary(sentences):\n",
" dict = {}\n",
"\n",
" for entry in sentences:\n",
" dict[entry[0].lower()] = entry\n",
"\n",
" return dict\n",
"\n",
"memory_dict = prepare_dictionary(translation_memory)\n",
"\n",
"def ice_lookup(input, prev_sentence, next_sentence): \n",
" sentence = input.lower()\n",
"\n",
" if prev_sentence.lower() in memory_dict and next_sentence.lower() in memory_dict and sentence in memory_dict:\n",
" return memory_dict[sentence]\n",
"\n",
" return []" " return []"
] ]
}, },
{
"cell_type": "code",
"execution_count": 94,
"id": "bdc1df76",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"('Wciśnij przycisk Enter', 'Press the ENTER button')"
]
},
"execution_count": 94,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"ice_lookup(\"Wciśnij przycisk Enter\", \"Sprawdź ustawienia sieciowe\", \"Drukarka jest wyłączona\")"
]
},
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "figured-server", "id": "figured-server",
@ -119,7 +155,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 3, "execution_count": 95,
"id": "fourth-pillow", "id": "fourth-pillow",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -141,7 +177,11 @@
"id": "graduate-theorem", "id": "graduate-theorem",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Odpowiedź:" "Odpowiedź: Nie, nie jest poprawna. Cechy:\n",
"- nieujemna (abs > 0)\n",
"- identyfikacja nie jest spelniona -> moga miec taka sama dlugosc, a byc inne\n",
"- symetryczna - wynik z wartosci bezwglednej\n",
"- nierownosc trojkata nie jest spelniona"
] ]
}, },
{ {
@ -154,7 +194,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 4, "execution_count": 96,
"id": "continued-christopher", "id": "continued-christopher",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -179,7 +219,7 @@
"id": "metallic-leave", "id": "metallic-leave",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Odpowiedź:" "Odpowiedź: z punktu widzenia cech, wszystkie cechy sa spelnione, jednak funkcja sama w sobie jest bezuyteczna poprzez to, ze wartosci sa stale. "
] ]
}, },
{ {
@ -206,7 +246,10 @@
"id": "bibliographic-stopping", "id": "bibliographic-stopping",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Odpowiedź:" "Odpowiedź: Tak, poniewaz spelnia cechy: \n",
"- nieujemnosci - zawsze dodatni lub zero gdy a i b jest rowny sobie\n",
"- symetria - dystans od a i b jest taki sam jak b i a\n",
"- nierownosc trojkata - dystans od ciągu A do C przez B jest zawsze mniejszy lub równy sumie dystansów od A do B i od B do C"
] ]
}, },
{ {
@ -223,7 +266,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 5, "execution_count": 97,
"id": "secondary-wrist", "id": "secondary-wrist",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -233,7 +276,7 @@
"2" "2"
] ]
}, },
"execution_count": 5, "execution_count": 97,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -254,7 +297,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 6, "execution_count": 98,
"id": "associate-tuner", "id": "associate-tuner",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -273,7 +316,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 7, "execution_count": 99,
"id": "focal-pathology", "id": "focal-pathology",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -283,7 +326,7 @@
"0.9166666666666666" "0.9166666666666666"
] ]
}, },
"execution_count": 7, "execution_count": 99,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -294,7 +337,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 8, "execution_count": 100,
"id": "roman-ceiling", "id": "roman-ceiling",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -304,7 +347,7 @@
"0.9428571428571428" "0.9428571428571428"
] ]
}, },
"execution_count": 8, "execution_count": 100,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -315,7 +358,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 9, "execution_count": 101,
"id": "invisible-cambodia", "id": "invisible-cambodia",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -325,7 +368,7 @@
"0.631578947368421" "0.631578947368421"
] ]
}, },
"execution_count": 9, "execution_count": 101,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -344,13 +387,61 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 10, "execution_count": 102,
"id": "genetic-cradle", "id": "genetic-cradle",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"def fuzzy_lookup(sentence, threshold):\n", "def fuzzy_lookup(sentence, threshold):\n",
" return []" " col = []\n",
"\n",
" for entry in translation_memory:\n",
" if (levenshtein_similarity(entry[0], sentence)) >= threshold:\n",
" col.append(entry)\n",
" \n",
" return col"
]
},
{
"cell_type": "code",
"execution_count": 103,
"id": "57fb39b9",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[]"
]
},
"execution_count": 103,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"fuzzy_lookup('Spróbuj wyłączyć i włączyć komputer', 0.7)"
]
},
{
"cell_type": "code",
"execution_count": 104,
"id": "94e1b3be",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[('Wciśnij przycisk Enter', 'Press the ENTER button')]"
]
},
"execution_count": 104,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"fuzzy_lookup('Wciśnij przycisk escape', 0.7)"
] ]
} }
], ],
@ -373,7 +464,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.8.10" "version": "3.7.9"
}, },
"subtitle": "2. Zaawansowane użycie pamięci tłumaczeń", "subtitle": "2. Zaawansowane użycie pamięci tłumaczeń",
"title": "Komputerowe wspomaganie tłumaczenia", "title": "Komputerowe wspomaganie tłumaczenia",

70
lab/lab_03.ipynb
View File

@ -86,7 +86,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 1, "execution_count": 31,
"id": "loving-prince", "id": "loving-prince",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -110,12 +110,12 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 2, "execution_count": 32,
"id": "bound-auction", "id": "bound-auction",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"dictionary = ['program', 'application', 'applet' 'compile']" "dictionary = ['program', 'application', 'applet', 'compile']"
] ]
}, },
{ {
@ -128,13 +128,47 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 3, "execution_count": 33,
"id": "cognitive-cedar", "id": "cognitive-cedar",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"def terminology_lookup():\n", "import re\n",
" return []" "\n",
"def terminology_lookup(txt, labels):\n",
" results = []\n",
"\n",
" for label in labels:\n",
" results.append((\n",
" label,\n",
" [(m.start(), m.end() - 1) for m in re.finditer(label, txt)]\n",
" ))\n",
"\n",
" return results"
]
},
{
"cell_type": "code",
"execution_count": 34,
"id": "7cc3ad1f",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[('program', [(14, 20), (291, 297), (468, 474), (516, 522), (533, 539)]),\n",
" ('application', [(80, 90), (164, 174), (322, 332)]),\n",
" ('applet', [(302, 307)]),\n",
" ('compile', [(56, 62)])]"
]
},
"execution_count": 34,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"terminology_lookup(text, dictionary)"
] ]
}, },
{ {
@ -161,7 +195,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 4, "execution_count": 35,
"id": "tribal-attention", "id": "tribal-attention",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -205,7 +239,7 @@
"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 +252,7 @@
"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 +266,7 @@
"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 +282,7 @@
"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 +294,7 @@
"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",
@ -302,7 +336,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 5, "execution_count": 36,
"id": "surgical-demonstration", "id": "surgical-demonstration",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -337,7 +371,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 6, "execution_count": 37,
"id": "superb-butterfly", "id": "superb-butterfly",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -356,7 +390,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 7, "execution_count": 38,
"id": "acting-tolerance", "id": "acting-tolerance",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -374,7 +408,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 8, "execution_count": 39,
"id": "eight-redhead", "id": "eight-redhead",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -393,7 +427,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 9, "execution_count": 40,
"id": "monetary-mambo", "id": "monetary-mambo",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -422,7 +456,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.8.10" "version": "3.7.9"
}, },
"subtitle": "3. Terminologia", "subtitle": "3. Terminologia",
"title": "Komputerowe wspomaganie tłumaczenia", "title": "Komputerowe wspomaganie tłumaczenia",