mirror of
https://github.com/gsi-upm/sitc
synced 2024-11-22 06:22:29 +00:00
Added tag UPenn example
This commit is contained in:
cif2cif
parent
e88e144a50
commit
c55a1c077b
@ -61,7 +61,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 1,
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
@ -109,11 +109,19 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 30,
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"outputs": [],
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"[('I', 'PRON'), ('purchased', 'VERB'), ('this', 'DET'), ('Dell', 'NOUN'), ('monitor', 'NOUN'), ('because', 'ADP'), ('of', 'ADP'), ('budgetary', 'ADJ'), ('concerns', 'NOUN'), ('.', '.'), ('This', 'DET'), ('item', 'NOUN'), ('was', 'VERB'), ('the', 'DET'), ('most', 'ADV'), ('inexpensive', 'ADJ'), ('17', 'NUM'), ('inch', 'NOUN'), ('Apple', 'NOUN'), ('monitor', 'NOUN'), ('available', 'ADJ'), ('to', 'PRT'), ('me', 'PRON'), ('at', 'ADP'), ('the', 'DET'), ('time', 'NOUN'), ('I', 'PRON'), ('made', 'VERB'), ('the', 'DET'), ('purchase', 'NOUN'), ('.', '.'), ('My', 'PRON'), ('overall', 'ADJ'), ('experience', 'NOUN'), ('with', 'ADP'), ('this', 'DET'), ('monitor', 'NOUN'), ('was', 'VERB'), ('very', 'ADV'), ('poor', 'ADJ'), ('.', '.'), ('When', 'ADV'), ('the', 'DET'), ('screen', 'NOUN'), ('was', 'VERB'), (\"n't\", 'ADV'), ('contracting', 'VERB'), ('or', 'CONJ'), ('glitching', 'VERB'), ('the', 'DET'), ('overall', 'ADJ'), ('picture', 'NOUN'), ('quality', 'NOUN'), ('was', 'VERB'), ('poor', 'ADJ'), ('to', 'PRT'), ('fair', 'VERB'), ('.', '.'), ('I', 'PRON'), (\"'ve\", 'VERB'), ('viewed', 'VERB'), ('numerous', 'ADJ'), ('different', 'ADJ'), ('monitor', 'NOUN'), ('models', 'NOUN'), ('since', 'ADP'), ('I', 'PRON'), (\"'m\", 'VERB'), ('a', 'DET'), ('college', 'NOUN'), ('student', 'NOUN'), ('at', 'ADP'), ('UPM', 'NOUN'), ('in', 'ADP'), ('Madrid', 'NOUN'), ('and', 'CONJ'), ('this', 'DET'), ('particular', 'ADJ'), ('monitor', 'NOUN'), ('had', 'VERB'), ('as', 'ADP'), ('poor', 'ADJ'), ('of', 'ADP'), ('picture', 'NOUN'), ('quality', 'NOUN'), ('as', 'ADP'), ('any', 'DET'), ('I', 'PRON'), (\"'ve\", 'VERB'), ('seen', 'VERB'), ('.', '.')]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from nltk import pos_tag, word_tokenize\n",
|
||||
"print (pos_tag(word_tokenize(review), tagset='universal'))"
|
||||
@ -123,16 +131,213 @@
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Based on this POS info, we could use correctly now the WordNetLemmatizer. The WordNetLemmatizer only is interesting for 4 POS categories: ADJ, ADV, NOUN, and VERB."
|
||||
"We could have used another tagset for POS, such as UPenn."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 28,
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"outputs": [],
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"[('I', 'PRP'), ('purchased', 'VBD'), ('this', 'DT'), ('Dell', 'NNP'), ('monitor', 'NN'), ('because', 'IN'), ('of', 'IN'), ('budgetary', 'JJ'), ('concerns', 'NNS'), ('.', '.'), ('This', 'DT'), ('item', 'NN'), ('was', 'VBD'), ('the', 'DT'), ('most', 'RBS'), ('inexpensive', 'JJ'), ('17', 'CD'), ('inch', 'NN'), ('Apple', 'NNP'), ('monitor', 'NN'), ('available', 'JJ'), ('to', 'TO'), ('me', 'PRP'), ('at', 'IN'), ('the', 'DT'), ('time', 'NN'), ('I', 'PRP'), ('made', 'VBD'), ('the', 'DT'), ('purchase', 'NN'), ('.', '.'), ('My', 'PRP$'), ('overall', 'JJ'), ('experience', 'NN'), ('with', 'IN'), ('this', 'DT'), ('monitor', 'NN'), ('was', 'VBD'), ('very', 'RB'), ('poor', 'JJ'), ('.', '.'), ('When', 'WRB'), ('the', 'DT'), ('screen', 'NN'), ('was', 'VBD'), (\"n't\", 'RB'), ('contracting', 'VBG'), ('or', 'CC'), ('glitching', 'VBG'), ('the', 'DT'), ('overall', 'JJ'), ('picture', 'NN'), ('quality', 'NN'), ('was', 'VBD'), ('poor', 'JJ'), ('to', 'TO'), ('fair', 'VB'), ('.', '.'), ('I', 'PRP'), (\"'ve\", 'VBP'), ('viewed', 'VBN'), ('numerous', 'JJ'), ('different', 'JJ'), ('monitor', 'NN'), ('models', 'NNS'), ('since', 'IN'), ('I', 'PRP'), (\"'m\", 'VBP'), ('a', 'DT'), ('college', 'NN'), ('student', 'NN'), ('at', 'IN'), ('UPM', 'NNP'), ('in', 'IN'), ('Madrid', 'NNP'), ('and', 'CC'), ('this', 'DT'), ('particular', 'JJ'), ('monitor', 'NN'), ('had', 'VBD'), ('as', 'IN'), ('poor', 'JJ'), ('of', 'IN'), ('picture', 'NN'), ('quality', 'NN'), ('as', 'IN'), ('any', 'DT'), ('I', 'PRP'), (\"'ve\", 'VBP'), ('seen', 'VBN'), ('.', '.')]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print (pos_tag(word_tokenize(review)))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The meaning of these tags can be obtained here:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 29,
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"$: dollar\n",
|
||||
" $ -$ --$ A$ C$ HK$ M$ NZ$ S$ U.S.$ US$\n",
|
||||
"'': closing quotation mark\n",
|
||||
" ' ''\n",
|
||||
"(: opening parenthesis\n",
|
||||
" ( [ {\n",
|
||||
"): closing parenthesis\n",
|
||||
" ) ] }\n",
|
||||
",: comma\n",
|
||||
" ,\n",
|
||||
"--: dash\n",
|
||||
" --\n",
|
||||
".: sentence terminator\n",
|
||||
" . ! ?\n",
|
||||
":: colon or ellipsis\n",
|
||||
" : ; ...\n",
|
||||
"CC: conjunction, coordinating\n",
|
||||
" & 'n and both but either et for less minus neither nor or plus so\n",
|
||||
" therefore times v. versus vs. whether yet\n",
|
||||
"CD: numeral, cardinal\n",
|
||||
" mid-1890 nine-thirty forty-two one-tenth ten million 0.5 one forty-\n",
|
||||
" seven 1987 twenty '79 zero two 78-degrees eighty-four IX '60s .025\n",
|
||||
" fifteen 271,124 dozen quintillion DM2,000 ...\n",
|
||||
"DT: determiner\n",
|
||||
" all an another any both del each either every half la many much nary\n",
|
||||
" neither no some such that the them these this those\n",
|
||||
"EX: existential there\n",
|
||||
" there\n",
|
||||
"FW: foreign word\n",
|
||||
" gemeinschaft hund ich jeux habeas Haementeria Herr K'ang-si vous\n",
|
||||
" lutihaw alai je jour objets salutaris fille quibusdam pas trop Monte\n",
|
||||
" terram fiche oui corporis ...\n",
|
||||
"IN: preposition or conjunction, subordinating\n",
|
||||
" astride among uppon whether out inside pro despite on by throughout\n",
|
||||
" below within for towards near behind atop around if like until below\n",
|
||||
" next into if beside ...\n",
|
||||
"JJ: adjective or numeral, ordinal\n",
|
||||
" third ill-mannered pre-war regrettable oiled calamitous first separable\n",
|
||||
" ectoplasmic battery-powered participatory fourth still-to-be-named\n",
|
||||
" multilingual multi-disciplinary ...\n",
|
||||
"JJR: adjective, comparative\n",
|
||||
" bleaker braver breezier briefer brighter brisker broader bumper busier\n",
|
||||
" calmer cheaper choosier cleaner clearer closer colder commoner costlier\n",
|
||||
" cozier creamier crunchier cuter ...\n",
|
||||
"JJS: adjective, superlative\n",
|
||||
" calmest cheapest choicest classiest cleanest clearest closest commonest\n",
|
||||
" corniest costliest crassest creepiest crudest cutest darkest deadliest\n",
|
||||
" dearest deepest densest dinkiest ...\n",
|
||||
"LS: list item marker\n",
|
||||
" A A. B B. C C. D E F First G H I J K One SP-44001 SP-44002 SP-44005\n",
|
||||
" SP-44007 Second Third Three Two * a b c d first five four one six three\n",
|
||||
" two\n",
|
||||
"MD: modal auxiliary\n",
|
||||
" can cannot could couldn't dare may might must need ought shall should\n",
|
||||
" shouldn't will would\n",
|
||||
"NN: noun, common, singular or mass\n",
|
||||
" common-carrier cabbage knuckle-duster Casino afghan shed thermostat\n",
|
||||
" investment slide humour falloff slick wind hyena override subhumanity\n",
|
||||
" machinist ...\n",
|
||||
"NNP: noun, proper, singular\n",
|
||||
" Motown Venneboerger Czestochwa Ranzer Conchita Trumplane Christos\n",
|
||||
" Oceanside Escobar Kreisler Sawyer Cougar Yvette Ervin ODI Darryl CTCA\n",
|
||||
" Shannon A.K.C. Meltex Liverpool ...\n",
|
||||
"NNPS: noun, proper, plural\n",
|
||||
" Americans Americas Amharas Amityvilles Amusements Anarcho-Syndicalists\n",
|
||||
" Andalusians Andes Andruses Angels Animals Anthony Antilles Antiques\n",
|
||||
" Apache Apaches Apocrypha ...\n",
|
||||
"NNS: noun, common, plural\n",
|
||||
" undergraduates scotches bric-a-brac products bodyguards facets coasts\n",
|
||||
" divestitures storehouses designs clubs fragrances averages\n",
|
||||
" subjectivists apprehensions muses factory-jobs ...\n",
|
||||
"PDT: pre-determiner\n",
|
||||
" all both half many quite such sure this\n",
|
||||
"POS: genitive marker\n",
|
||||
" ' 's\n",
|
||||
"PRP: pronoun, personal\n",
|
||||
" hers herself him himself hisself it itself me myself one oneself ours\n",
|
||||
" ourselves ownself self she thee theirs them themselves they thou thy us\n",
|
||||
"PRP$: pronoun, possessive\n",
|
||||
" her his mine my our ours their thy your\n",
|
||||
"RB: adverb\n",
|
||||
" occasionally unabatingly maddeningly adventurously professedly\n",
|
||||
" stirringly prominently technologically magisterially predominately\n",
|
||||
" swiftly fiscally pitilessly ...\n",
|
||||
"RBR: adverb, comparative\n",
|
||||
" further gloomier grander graver greater grimmer harder harsher\n",
|
||||
" healthier heavier higher however larger later leaner lengthier less-\n",
|
||||
" perfectly lesser lonelier longer louder lower more ...\n",
|
||||
"RBS: adverb, superlative\n",
|
||||
" best biggest bluntest earliest farthest first furthest hardest\n",
|
||||
" heartiest highest largest least less most nearest second tightest worst\n",
|
||||
"RP: particle\n",
|
||||
" aboard about across along apart around aside at away back before behind\n",
|
||||
" by crop down ever fast for forth from go high i.e. in into just later\n",
|
||||
" low more off on open out over per pie raising start teeth that through\n",
|
||||
" under unto up up-pp upon whole with you\n",
|
||||
"SYM: symbol\n",
|
||||
" % & ' '' ''. ) ). * + ,. < = > @ A[fj] U.S U.S.S.R * ** ***\n",
|
||||
"TO: \"to\" as preposition or infinitive marker\n",
|
||||
" to\n",
|
||||
"UH: interjection\n",
|
||||
" Goodbye Goody Gosh Wow Jeepers Jee-sus Hubba Hey Kee-reist Oops amen\n",
|
||||
" huh howdy uh dammit whammo shucks heck anyways whodunnit honey golly\n",
|
||||
" man baby diddle hush sonuvabitch ...\n",
|
||||
"VB: verb, base form\n",
|
||||
" ask assemble assess assign assume atone attention avoid bake balkanize\n",
|
||||
" bank begin behold believe bend benefit bevel beware bless boil bomb\n",
|
||||
" boost brace break bring broil brush build ...\n",
|
||||
"VBD: verb, past tense\n",
|
||||
" dipped pleaded swiped regummed soaked tidied convened halted registered\n",
|
||||
" cushioned exacted snubbed strode aimed adopted belied figgered\n",
|
||||
" speculated wore appreciated contemplated ...\n",
|
||||
"VBG: verb, present participle or gerund\n",
|
||||
" telegraphing stirring focusing angering judging stalling lactating\n",
|
||||
" hankerin' alleging veering capping approaching traveling besieging\n",
|
||||
" encrypting interrupting erasing wincing ...\n",
|
||||
"VBN: verb, past participle\n",
|
||||
" multihulled dilapidated aerosolized chaired languished panelized used\n",
|
||||
" experimented flourished imitated reunifed factored condensed sheared\n",
|
||||
" unsettled primed dubbed desired ...\n",
|
||||
"VBP: verb, present tense, not 3rd person singular\n",
|
||||
" predominate wrap resort sue twist spill cure lengthen brush terminate\n",
|
||||
" appear tend stray glisten obtain comprise detest tease attract\n",
|
||||
" emphasize mold postpone sever return wag ...\n",
|
||||
"VBZ: verb, present tense, 3rd person singular\n",
|
||||
" bases reconstructs marks mixes displeases seals carps weaves snatches\n",
|
||||
" slumps stretches authorizes smolders pictures emerges stockpiles\n",
|
||||
" seduces fizzes uses bolsters slaps speaks pleads ...\n",
|
||||
"WDT: WH-determiner\n",
|
||||
" that what whatever which whichever\n",
|
||||
"WP: WH-pronoun\n",
|
||||
" that what whatever whatsoever which who whom whosoever\n",
|
||||
"WP$: WH-pronoun, possessive\n",
|
||||
" whose\n",
|
||||
"WRB: Wh-adverb\n",
|
||||
" how however whence whenever where whereby whereever wherein whereof why\n",
|
||||
"``: opening quotation mark\n",
|
||||
" ` ``\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"nltk.help.upenn_tagset()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We are going to use the Univeral tagset in this example. Based on this POS info, we could use correctly now the WordNetLemmatizer. The WordNetLemmatizer only is interesting for 4 POS categories: ADJ, ADV, NOUN, and VERB. This is because WordNet lemmatizer will only lemmatize adjectives, adverbs, nouns and verbs, and it needs that all the provided tags are in [n, a, r, v]."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"['I', 'purchase', 'Dell', 'monitor', 'because', 'of', 'budgetary', 'concern', 'item', 'be', 'most', 'inexpensive', '17', 'inch', 'Apple', 'monitor', 'available', 'me', 'at', 'time', 'I', 'make', 'purchase', 'My', 'overall', 'experience', 'with', 'monitor', 'be', 'very', 'poor', 'When', 'screen', 'be', \"n't\", 'contract', 'or', 'glitching', 'overall', 'picture', 'quality', 'be', 'poor', 'fair', 'I', \"'ve\", 'view', 'numerous', 'different', 'monitor', 'model', 'since', 'I', \"'m\", 'college', 'student', 'at', 'UPM', 'in', 'Madrid', 'and', 'particular', 'monitor', 'have', 'a', 'poor', 'of', 'picture', 'quality', 'a', 'I', \"'ve\", 'see']\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from nltk.stem import WordNetLemmatizer\n",
|
||||
"\n",
|
||||
@ -156,16 +361,115 @@
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Named Entity Recognition (NER) is an information retrieval for identifying named entities of places, organisation of persons. NER usually relies in a tagged corpus. NER algorithms can be trained for new corpora."
|
||||
"Named Entity Recognition (NER) is an information retrieval for identifying named entities of places, organisation of persons. NER usually relies in a tagged corpus. NER algorithms can be trained for new corpora. Here we are using the Brown tagset (http://www.comp.leeds.ac.uk/ccalas/tagsets/brown.html)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 4,
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"outputs": [],
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"(S\n",
|
||||
" I/PRP\n",
|
||||
" purchased/VBD\n",
|
||||
" this/DT\n",
|
||||
" (ORGANIZATION Dell/NNP)\n",
|
||||
" monitor/NN\n",
|
||||
" because/IN\n",
|
||||
" of/IN\n",
|
||||
" budgetary/JJ\n",
|
||||
" concerns/NNS\n",
|
||||
" ./.\n",
|
||||
" This/DT\n",
|
||||
" item/NN\n",
|
||||
" was/VBD\n",
|
||||
" the/DT\n",
|
||||
" most/RBS\n",
|
||||
" inexpensive/JJ\n",
|
||||
" 17/CD\n",
|
||||
" inch/NN\n",
|
||||
" Apple/NNP\n",
|
||||
" monitor/NN\n",
|
||||
" available/JJ\n",
|
||||
" to/TO\n",
|
||||
" me/PRP\n",
|
||||
" at/IN\n",
|
||||
" the/DT\n",
|
||||
" time/NN\n",
|
||||
" I/PRP\n",
|
||||
" made/VBD\n",
|
||||
" the/DT\n",
|
||||
" purchase/NN\n",
|
||||
" ./.\n",
|
||||
" My/PRP$\n",
|
||||
" overall/JJ\n",
|
||||
" experience/NN\n",
|
||||
" with/IN\n",
|
||||
" this/DT\n",
|
||||
" monitor/NN\n",
|
||||
" was/VBD\n",
|
||||
" very/RB\n",
|
||||
" poor/JJ\n",
|
||||
" ./.\n",
|
||||
" When/WRB\n",
|
||||
" the/DT\n",
|
||||
" screen/NN\n",
|
||||
" was/VBD\n",
|
||||
" n't/RB\n",
|
||||
" contracting/VBG\n",
|
||||
" or/CC\n",
|
||||
" glitching/VBG\n",
|
||||
" the/DT\n",
|
||||
" overall/JJ\n",
|
||||
" picture/NN\n",
|
||||
" quality/NN\n",
|
||||
" was/VBD\n",
|
||||
" poor/JJ\n",
|
||||
" to/TO\n",
|
||||
" fair/VB\n",
|
||||
" ./.\n",
|
||||
" I/PRP\n",
|
||||
" 've/VBP\n",
|
||||
" viewed/VBN\n",
|
||||
" numerous/JJ\n",
|
||||
" different/JJ\n",
|
||||
" monitor/NN\n",
|
||||
" models/NNS\n",
|
||||
" since/IN\n",
|
||||
" I/PRP\n",
|
||||
" 'm/VBP\n",
|
||||
" a/DT\n",
|
||||
" college/NN\n",
|
||||
" student/NN\n",
|
||||
" at/IN\n",
|
||||
" (ORGANIZATION UPM/NNP)\n",
|
||||
" in/IN\n",
|
||||
" (GPE Madrid/NNP)\n",
|
||||
" and/CC\n",
|
||||
" this/DT\n",
|
||||
" particular/JJ\n",
|
||||
" monitor/NN\n",
|
||||
" had/VBD\n",
|
||||
" as/IN\n",
|
||||
" poor/JJ\n",
|
||||
" of/IN\n",
|
||||
" picture/NN\n",
|
||||
" quality/NN\n",
|
||||
" as/IN\n",
|
||||
" any/DT\n",
|
||||
" I/PRP\n",
|
||||
" 've/VBP\n",
|
||||
" seen/VBN\n",
|
||||
" ./.)\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from nltk import ne_chunk, pos_tag, word_tokenize\n",
|
||||
"ne_tagged = ne_chunk(pos_tag(word_tokenize(review)), binary=False)\n",
|
||||
@ -206,7 +510,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 5,
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
@ -229,11 +533,90 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 6,
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"outputs": [],
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"(S\n",
|
||||
" I/PRON\n",
|
||||
" purchased/VERB\n",
|
||||
" (NP this/DET Dell/NOUN monitor/NOUN)\n",
|
||||
" because/ADP\n",
|
||||
" of/ADP\n",
|
||||
" (NP budgetary/ADJ concerns/NOUN)\n",
|
||||
" ./.\n",
|
||||
" (NP This/DET item/NOUN)\n",
|
||||
" was/VERB\n",
|
||||
" (NP\n",
|
||||
" the/DET\n",
|
||||
" most/ADV\n",
|
||||
" inexpensive/ADJ\n",
|
||||
" 17/NUM\n",
|
||||
" inch/NOUN\n",
|
||||
" Apple/NOUN\n",
|
||||
" monitor/NOUN)\n",
|
||||
" available/ADJ\n",
|
||||
" to/PRT\n",
|
||||
" me/PRON\n",
|
||||
" at/ADP\n",
|
||||
" (NP the/DET time/NOUN)\n",
|
||||
" I/PRON\n",
|
||||
" made/VERB\n",
|
||||
" (NP the/DET purchase/NOUN)\n",
|
||||
" ./.\n",
|
||||
" (NP My/PRON overall/ADJ experience/NOUN)\n",
|
||||
" with/ADP\n",
|
||||
" (NP this/DET monitor/NOUN)\n",
|
||||
" was/VERB\n",
|
||||
" very/ADV\n",
|
||||
" poor/ADJ\n",
|
||||
" ./.\n",
|
||||
" When/ADV\n",
|
||||
" (NP the/DET screen/NOUN)\n",
|
||||
" was/VERB\n",
|
||||
" n't/ADV\n",
|
||||
" contracting/VERB\n",
|
||||
" or/CONJ\n",
|
||||
" glitching/VERB\n",
|
||||
" (NP the/DET overall/ADJ picture/NOUN quality/NOUN)\n",
|
||||
" was/VERB\n",
|
||||
" poor/ADJ\n",
|
||||
" to/PRT\n",
|
||||
" fair/VERB\n",
|
||||
" ./.\n",
|
||||
" I/PRON\n",
|
||||
" 've/VERB\n",
|
||||
" viewed/VERB\n",
|
||||
" (NP numerous/ADJ different/ADJ monitor/NOUN models/NOUN)\n",
|
||||
" since/ADP\n",
|
||||
" I/PRON\n",
|
||||
" 'm/VERB\n",
|
||||
" (NP a/DET college/NOUN student/NOUN)\n",
|
||||
" at/ADP\n",
|
||||
" (NP UPM/NOUN)\n",
|
||||
" in/ADP\n",
|
||||
" (NP Madrid/NOUN)\n",
|
||||
" and/CONJ\n",
|
||||
" (NP this/DET particular/ADJ monitor/NOUN)\n",
|
||||
" had/VERB\n",
|
||||
" as/ADP\n",
|
||||
" poor/ADJ\n",
|
||||
" of/ADP\n",
|
||||
" (NP picture/NOUN quality/NOUN)\n",
|
||||
" as/ADP\n",
|
||||
" any/DET\n",
|
||||
" I/PRON\n",
|
||||
" 've/VERB\n",
|
||||
" seen/VERB\n",
|
||||
" ./.)\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from nltk.chunk.regexp import *\n",
|
||||
"pattern = \"\"\"NP: {<PRON><ADJ><NOUN>+} \n",
|
||||
@ -257,11 +640,37 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 7,
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"outputs": [],
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Tree('NP', [('this', 'DET'), ('Dell', 'NOUN'), ('monitor', 'NOUN')]),\n",
|
||||
" Tree('NP', [('budgetary', 'ADJ'), ('concerns', 'NOUN')]),\n",
|
||||
" Tree('NP', [('This', 'DET'), ('item', 'NOUN')]),\n",
|
||||
" Tree('NP', [('the', 'DET'), ('most', 'ADV'), ('inexpensive', 'ADJ'), ('17', 'NUM'), ('inch', 'NOUN'), ('Apple', 'NOUN'), ('monitor', 'NOUN')]),\n",
|
||||
" Tree('NP', [('the', 'DET'), ('time', 'NOUN')]),\n",
|
||||
" Tree('NP', [('the', 'DET'), ('purchase', 'NOUN')]),\n",
|
||||
" Tree('NP', [('My', 'PRON'), ('overall', 'ADJ'), ('experience', 'NOUN')]),\n",
|
||||
" Tree('NP', [('this', 'DET'), ('monitor', 'NOUN')]),\n",
|
||||
" Tree('NP', [('the', 'DET'), ('screen', 'NOUN')]),\n",
|
||||
" Tree('NP', [('the', 'DET'), ('overall', 'ADJ'), ('picture', 'NOUN'), ('quality', 'NOUN')]),\n",
|
||||
" Tree('NP', [('numerous', 'ADJ'), ('different', 'ADJ'), ('monitor', 'NOUN'), ('models', 'NOUN')]),\n",
|
||||
" Tree('NP', [('a', 'DET'), ('college', 'NOUN'), ('student', 'NOUN')]),\n",
|
||||
" Tree('NP', [('UPM', 'NOUN')]),\n",
|
||||
" Tree('NP', [('Madrid', 'NOUN')]),\n",
|
||||
" Tree('NP', [('this', 'DET'), ('particular', 'ADJ'), ('monitor', 'NOUN')]),\n",
|
||||
" Tree('NP', [('picture', 'NOUN'), ('quality', 'NOUN')])]"
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"def extractTrees(parsed_tree, category='NP'):\n",
|
||||
" return list(parsed_tree.subtrees(filter=lambda x: x.label()==category))\n",
|
||||
@ -271,11 +680,37 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 8,
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"outputs": [],
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"['this Dell monitor',\n",
|
||||
" 'budgetary concerns',\n",
|
||||
" 'This item',\n",
|
||||
" 'the most inexpensive 17 inch Apple monitor',\n",
|
||||
" 'the time',\n",
|
||||
" 'the purchase',\n",
|
||||
" 'My overall experience',\n",
|
||||
" 'this monitor',\n",
|
||||
" 'the screen',\n",
|
||||
" 'the overall picture quality',\n",
|
||||
" 'numerous different monitor models',\n",
|
||||
" 'a college student',\n",
|
||||
" 'UPM',\n",
|
||||
" 'Madrid',\n",
|
||||
" 'this particular monitor',\n",
|
||||
" 'picture quality']"
|
||||
]
|
||||
},
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"def extractStrings(parsed_tree, category='NP'):\n",
|
||||
" return [\" \".join(word for word, pos in vp.leaves()) for vp in extractTrees(parsed_tree, category)]\n",
|
||||
|
||||
Loading…
Reference in New Issue
Block a user