"everybody", "everyone", "everything", "less", "little", "much", "neither", "no one", "nobody", "nothing", "one", "other", "plenty", "somebody", "someone", "something", "both", "few", "fewer", "many", "others", "several", "all", "any", "more", "most", "none", "some", "such")) relative = list_checker(("that", "who", "which", "whom", "where", "whose")) reflexive = list_checker( ("myself", "yourself", "yourselves", "himself", "herself", "itself", "ourselves", "themselves", "oneself")) no_organization = list_checker( ("i", "me", "myself", "mine", "my", "yourself", "he", "him", "himself", "his", "she", "her", "herself", "hers", "here")) first_person = list_checker(("i", "me", "myself", "mine", "my", "we", "us", "ourself", "ourselves", "ours", "our")) second_person = list_checker( ("you", "yourself", "yours", "your", "yourselves")) third_person = list_checker( ("he", "him", "himself", "his", "she", "her", "herself", "hers", "her", "it", "itself", "its", "one", "oneself", "one's", "they", "them", "themself", "themselves", "theirs", "their", "they", "them", "'em", "themselves")) _others = list_checker(("who", "whom", "whose", "where", "when", "which")) all = lambda x: first_person(x) or second_person(x) or third_person( x) or _others(x) pleonastic = equality_checker("it")
# coding=utf-8 from corefgraph.resources.lambdas import list_checker, equality_checker, matcher, fail __author__ = 'Josu Bermudez <*****@*****.**>' # Is a root constituent root = list_checker(("root", "top", "ROOT", "TOP")) # Is a clause clause = matcher("^S") # Is a Noun phrase noun_phrase = equality_checker("NP") # Is a Noun phrase #prepositional_phrase = equality_checker("SP") # Is a Verb phrase verb_phrase = equality_checker("VP") # Is a particle constituent particle_constituent = equality_checker("PRT") # Is an interjection constituent past_participle_verb = equality_checker("VBN") # Is an interjection constituent interjection = equality_checker("INTJ") # Is a simple or subordinated clause
__author__ = 'Valeria Quochi <*****@*****.**>' # Is a root constituent root = list_checker(("root", "top", "ROOT", "TOP")) # Is a clause clause = list_checker(( "S", "SBAR", )) # Is a simple or subordinated clause simple_or_sub_phrase = clause # Is a Noun phrase noun_phrase = equality_checker("NP") # Is a Verb phrase verb_phrase = equality_checker("VP") # Is a Adverbial phrase adverbial_phrase = fail() # Is a complement direct complement_direct = list_checker(("CD", )) # Is a particle constituent particle_constituent = fail() # Is a past_participle verb constituent past_participle_verb = equality_checker("VBN")
# coding=utf-8 """ """ __author__ = 'Josu Bermudez <*****@*****.**>' __date__ = '3/13' # DD/MM/YY from corefgraph.resources.lambdas import list_checker, equality_checker, matcher, fail # Extracted from CoreNLP indefinite_articles = list_checker(("a", "an")) quantifiers = list_checker(("not", "every", "any", "none", "everything", "anything", "nothing", "all", "enough")) partitives = list_checker(( "half", "one", "two", "three", "four", "five", "six", "seven", "eight", "nine", "ten", "hundred", "thousand", "million", "billion", "tens", "dozens", "hundreds", "thousands", "millions", "billions", "group", "groups", "bunch", "number", "numbers", "pinch", "amount", "amount", "total", "all", "mile", "miles", "pounds")) partitive_particle = equality_checker("of")
pronoun = matcher("^PRON.*") personal_pronoun = matcher("^PRON.*PRS.*") relative_pronoun = matcher("^PRON.*REL.*") interrogative_pronoun = matcher("^PRON.*INT.*") mention_pronoun = lambda x: relative_pronoun(x) or personal_pronoun(x) # Nouns singular_common_noun = matcher("^NOUN.*SING.*") plural_common_noun = matcher("^NOUN.*PLUR.*") common_noun = matcher("^NOUN.*") proper_noun = matcher("^PROPN.*") noun = matcher("^PROPN|^NOUN") # Verbs verb = matcher("^VERB") modal = equality_checker("^AUX") mod_forms = lambda x: common_noun(x) or adjective(x) or verb(x) or cardinal(x) indefinites = fail() # Enumerations enumerable_mention_words = noun conjunction = equality_checker("CONJ") interjection = equality_checker("INTERJ") cardinal = equality_checker("CD") # Determinant determinant = lambda x: not verb(x) and matcher("DET") indefinite = lambda x: not verb(x) and matcher("IND") head_rules = noun
# coding=utf-8 from corefgraph.resources.lambdas import equality_checker, fail, matcher __author__ = 'Valeria Quochi <*****@*****.**>' __date__ = '5/16/2013' # features questions female = fail() male = fail() neutral = fail() singular = equality_checker("^NOU_CS") plural = equality_checker("^NOU_CP") animate = fail() inanimate = fail() # Adjectives adjective = matcher("^ADJ.*") # pronouns personal_pronoun = matcher("^PRO~PE") relative_pronoun = matcher("^PRO~RE") pronoun = matcher("^PRO") mention_pronoun = lambda x: relative_pronoun(x) or personal_pronoun(x) singular_common_noun = equality_checker("^NOU_CS") plural_common_noun = equality_checker("^NOU_CP") proper_noun = matcher("^NOU~PR") noun = matcher("^NOU.*") verbs = matcher("^V.*") modals = equality_checker("^VMO.*")
# Is a clause clause = list_checker(("S", "SENTENCE")) # Is a Noun phrase noun_phrase = list_checker(("SN", "GRUP.NOM", "SUJ")) # Is a Verb phrase verb_phrase = list_checker(("GRUP.VERB",)) # Is a complement direct complement_direct = list_checker(("CD",)) # Is a particle constituent particle_constituent = fail() # Is a past_participle verb constituent past_participle_verb = fail() # Is an interjection constituent interjection = equality_checker("INTERJECCIÓ") # Is a NER annotated into semantic tree ner_constituent = fail() # Is a simple or subordinated clause simple_or_sub_phrase = clause #TODO Remove this check mention_constituents = lambda x: noun_phrase(x) or complement_direct(x) enumerable = list_checker(("^SN", "GRUP.NOM"))
"emfatitzar", "suggerir", "recolsar", "suposar", "conjecturar", "sospitar", "jurar", "ensenyar", "dir", "testificar", "pensar", "amenaçar", "descobrir", "subratllar", "destacar", "emfatitzar", "urguir", "expressar", "jurar", "prometre", "avisa", "saludar", "desitjar", "qüestionar", "preocupar", "escriure")) generics_you_verbs = equality_checker("saps") pleonastic_verbs = list_checker(("ser", "estar", "semblar", "explicar"))
"determine", "disagree", "disclose", "discount", "discover", "discuss", "dismiss", "dispute", "disregard", "doubt", "emphasize", "encourage", "endorse", "equate", "estimate", "expect", "explain", "express", "extoll", "fear", "feel", "find", "forbid", "forecast", "foretell", "forget", "gather", "guarantee", "guess", "hear", "hint", "hope", "illustrate", "imagine", "imply", "indicate", "inform", "insert", "insist", "instruct", "interpret", "interview", "invite", "issue", "justify", "learn", "maintain", "mean", "mention", "negotiate", "note", "observe", "offer", "oppose", "order", "persuade", "pledge", "point", "point out", "praise", "pray", "predict", "prefer", "present", "promise", "prompt", "propose", "protest", "prove", "provoke", "question", "quote", "raise", "rally", "read", "reaffirm", "realise", "realize", "rebut", "recall", "reckon", "recommend", "refer", "reflect", "refuse", "refute", "reiterate", "reject", "relate", "remark", "remember", "remind", "repeat", "reply", "add_report", "request", "respond", "restate", "reveal", "rule", "say", "see", "show", "signal", "sing", "slam", "speculate", "spoke", "spread", "state", "stipulate", "stress", "suggest", "support", "suppose", "surmise", "suspect", "swear", "teach", "tell", "testify", "think", "threaten", "told", "uncover", "underline", "underscore", "urge", "voice", "vow", "warn", "welcome", "wish", "wonder", "worry", "write")) generics_you_verbs = equality_checker("know") pleonastic_verbs = list_checker(("is", "was", "became", "become")) pleonastic_verbs_full = list_checker( ("is", "was", "be", "becomes", "become", "became")) alternative_a_pleonastic_verbs = list_checker( ("seems", "appears", "means", "follows")) alternative_b_pleonastic_verbs = equality_checker("turns") alternative_c_pleonastic_verbs = list_checker(("be", "become"))
ADJ~IR : interrogative adjective ADJ~EX : exclamative adjective following lines modified accordingly TODO check correctedness adjective_qualif = "ADJ~QU" adjective_ord = "ADJ~OR" adjective_indef = "ADJ~IN" adjective_dem = "ADJ~DE" adjective_poss = "ADJ~PO" adjective_deitt = "ADJ~DI" adjective_interr = "ADJ~IR" adjective_excl = "ADJ~EX" """ _conjunctions = equality_checker("CONJ", ) # Usable functions # features questions female = fail() male = fail() neutral = fail() singular = fail() plural = fail() animate = fail() inanimate = fail() # Adjectives adjective = list_checker( (_adjective, _adjective_comparative, _adjective_superlative))
__author__ = 'Josu Bermudez <*****@*****.**>' # Is a root constituent root = list_checker(("root", "top", "ROOT", "TOP")) # Is a clause clause = list_checker(("S", "SENTENCE")) # Is a simple or subordinated clause simple_or_sub_phrase = clause # Is a Noun phrase noun_phrase = list_checker(("SN", "SUJ", "GRUP.NOM")) # Is a Verb phrase verb_phrase = equality_checker("GRUP.VERB") # Is a Adverbial phrase adverbial_phrase = equality_checker("SADV") # Is a complement direct complement_direct = equality_checker("CD") # Is a particle constituent particle_constituent = fail() # Is a past_participle verb constituent past_participle_verb = fail() # Is an interjection constituent interjection = equality_checker("INTERJECCIÓ")
plural = matcher("^NNP?S$") animate = fail() inanimate = fail() # Adjectives adjective = list_checker((_adjective, )) # Pronouns pronoun = list_checker((_personal_pronoun, _possessive_pronoun, _wh_pronoun, _wh_possessive_pronoun)) relative_pronoun = list_checker((_wh_pronoun, _wh_possessive_pronoun)) mention_pronoun = matcher("^PRP") # Nouns singular_common_noun = equality_checker(_noun) plural_common_noun = equality_checker(_noun_plural) proper_noun = list_checker((_proper_noun, _proper_noun_plural)) noun = lambda x: x is not None and (singular_common_noun(x) or plural_common_noun(x) or proper_noun(x)) # Verbs verb = list_checker(_verbs_list) modal = equality_checker(_modal) mod_forms = lambda x: x is not None and (x.startswith("N") or x.startswith( "JJ") or x.startswith("V") or x == "CD") indefinite = fail # Enumerations enumerable_mention_words = matcher("^NNP")