Teneo Developers

Part of Speech and Morphology

Morphological ANNOT objects

The Teneo NL Analyzers include Part-of-Speech (POS) Taggers and Morphological Analyzers for a number of languages; the POS and Morphological Input Processors are described further here.

The NLU Ontology and Semantic Network distinguishes morphological ANNOT Language Objects between POS Language Objects, which are meant to capture part of speech such as verb and noun; and MST Language Objects, which are meant to capture morpho-syntactic traits such as noun number and verb tense.

The languages with available Morphological ANNOT Language Objects are listed and can be accesses in the left-side menu.

Chinese (Mandarin)

The Chinese Analyzer input processor uses a state-of-the-art tokenizer and morphological analyzer to split the user inputs into tokens and annotate them with morphological and syntactic information.

The table below gives an overview of the morphological ANNOT Language Objects available in the Chinese Teneo NLU Ontology and Semantic Network.

Morphological ANNOT language objectAnnotation used as condition
ACTOR_员.ANNOTACTOR_YUAN
ACTOR_师.ANNOTACTOR_SHI
ACTOR_者.ANNOTACTOR_ZHE
ASPECT_PERFECTIVE.ANNOTASPECT_PERFECTIVE
ASPECT_了.ANNOTASPECT_PERFECTIVE_LE
ASPECT_在.ANNOTASPECT_PREVERBAL_PROGRESSIVE_ZAI
ASPECT_正在.ANNOTASPECT_PREVERBAL_PROGRESSIVE_ZHENGZAI
ASPECT_着.ANNOTASPECT_PROGRESSIVE_ZHE
ASPECT_过.ANNOTASPECT_EXPERIENTIAL_GUO
CITY_城.ANNOTCITY_CHENG
CITY_市.ANNOTCITY_SHI
COMPARATIVE_于.ANNOTCOMPARATIVE_YU
DIR_上.ANNOTDIR_NONDEICTIC_SHANG
DIR_下.ANNOTDIR_NONDEICTIC_XIA
DIR_出.ANNOTDIR_NONDEICTIC_CHU
DIR_去.ANNOTDIR_DEICTIC_QU
DIR_回.ANNOTDIR_NONDEICTIC_HUI
DIR_开.ANNOTDIR_NONDEICTIC_KAI
DIR_来.ANNOTDIR_DEICTIC_LAI
DIR_起.ANNOTDIR_NONDEICTIC_QI
DIR_过.ANNOTDIR_NONDEICTIC_GUO
DIR_进.ANNOTDIR_NONDEICTIC_JIN
ERHUA_儿.ANNOTRCOLORING_ERHUA
LOC_上.ANNOTLOC_ON_SHANG
LOC_下.ANNOTLOC_UNDER_XIA
LOC_中.ANNOTLOC_IN_ZHONG
LOC_内.ANNOTLOC_INSIDE_NEI
LOC_前.ANNOTLOC_BEFORE_QIAN
LOC_后.ANNOTLOC_BEHIND_HOU
LOC_外.ANNOTLOC_OUTSIDE_WAI
LOC_旁.ANNOTLOC_NEXTTO_PANG
LOC_里.ANNOTLOC_INSIDE_LI
MODE_IMPERATIVE.ANNOTMODE_IMPERATIVE
MST_ASPECT.ANNOTASPECT.POS
MST_LOCALIZER.ANNOTLOC.POS
MST_PROPER.ANNOTPROPER.POS
MST_RESULTATIVE.ANNOTRESULTATIVE.POS
MST_TEMPORAL.ANNOTTEMPORAL.POS
NEG_不.ANNOTNEG_BU
NEG_别.ANNOTNEG_BIE
NEG_否.ANNOTNEG_FOU
NEG_没.ANNOTNEG_MEI
NEG_没有.ANNOTNEG_MEIYOU
PLURAL_们.ANNOTPLURAL_MEN
POS_ADJECTIVE.ANNOTADJ.POS
POS_ADVERB.ANNOTADV.POS
POS_CARDINAL.ANNOTCARDINAL.POS
POS_FOREIGN.ANNOTFOREIGN.POS
POS_FW.ANNOTBA.POS, CC.POS, CS.POS, DEC.POS, DEG.POS, DET.POS, ETC.POS, FOREIGN.POS, INTERJ.POS, LB.POS, MANNER.POS, MSP.POS, ONOMAT.POS, PARTICLE.POS, PREP.POS, SB.POS, SENTFINP.POS
POS_INTERJECTION.ANNOTINTERJ.POS
POS_MEASURE.ANNOTMEASURE.POS
POS_NOUN.ANNOTNN.POS
POS_ORDINAL.ANNOTORDINAL.POS
POS_PARTICLE.ANNOTPARTICLE.POS
POS_PRONOUN.ANNOTPRON.POS
POS_PUNCTUATION.ANNOTPUNCT.POS
POS_VC.ANNOTVC.POS
POS_VE.ANNOTVE.POS
POS_VERB.ANNOTVB.POS
POS_VV.ANNOTVV.POS
PROPERTY_度.ANNOTPROPERTY_DU
PROPERTY_性.ANNOTPROPERTY_XING
PROVINCE_省.ANNOTPROVINCE_SHENG
REDUP.ANNOTREDUP
RESULT_住.ANNOTRESULT_ZHU
RESULT_到.ANNOTRESULT_DAO
RESULT_好.ANNOTRESULT_HAO
RESULT_完.ANNOTRESULT_WAN
RESULT_成.ANNOTRESULT_CHENG
RESULT_掉.ANNOTRESULT_DIAO
RESULT_起.ANNOTRESULT_QI
SPLIT_上台.ANNOTSPLIT_SHANGTAI
SPLIT_上当.ANNOTSPLIT_SHANGDANG
SPLIT_下台.ANNOTSPLIT_XIATAI
SPLIT_丢人.ANNOTSPLIT_DIUREN
SPLIT_争气.ANNOTSPLIT_ZHENGQI
SPLIT_交手.ANNOTSPLIT_JIAOSHOU
SPLIT_伤人.ANNOTSPLIT_SHANGREN
SPLIT_伤心.ANNOTSPLIT_SHANGXIN
SPLIT_伸手.ANNOTSPLIT_SHENSHOU
SPLIT_住院.ANNOTSPLIT_ZHUYUAN
SPLIT_作战.ANNOTSPLIT_ZUOZHAN
SPLIT_作文.ANNOTSPLIT_ZUOWEN
SPLIT_作案.ANNOTSPLIT_ZUOAN
SPLIT_做客.ANNOTSPLIT_ZUOKE
SPLIT_像样.ANNOTSPLIT_XIANGYANG
SPLIT_入学.ANNOTSPLIT_RUXUE
SPLIT_减产.ANNOTSPLIT_JIANCHAN
SPLIT_出名.ANNOTSPLIT_CHUMING
SPLIT_出差.ANNOTSPLIT_CHUCHAI
SPLIT_出神.ANNOTSPLIT_CHUSHEN
SPLIT_出门.ANNOTSPLIT_CHUMEN
SPLIT_出面.ANNOTSPLIT_CHUMIAN
SPLIT_分红.ANNOTSPLIT_FENHONG
SPLIT_到期.ANNOTSPLIT_DAOQI
SPLIT_办公.ANNOTSPLIT_BANGONG
SPLIT_办学.ANNOTSPLIT_BANXUE
SPLIT_加工.ANNOTSPLIT_JIAGONG
SPLIT_加油.ANNOTSPLIT_JIAYOU
SPLIT_动身.ANNOTSPLIT_DONGSHEN
SPLIT_劳驾.ANNOTSPLIT_LAOJIA
SPLIT_升学.ANNOTSPLIT_SHENGXUE
SPLIT_及格.ANNOTSPLIT_JIGE
SPLIT_发炎.ANNOTSPLIT_FAYAN
SPLIT_叹气.ANNOTSPLIT_TANQI
SPLIT_吃亏.ANNOTSPLIT_CHIKUI
SPLIT_吃惊.ANNOTSPLIT_CHIJING
SPLIT_吃苦.ANNOTSPLIT_CHIKU
SPLIT_听话.ANNOTSPLIT_TINGHUA
SPLIT_吵嘴.ANNOTSPLIT_CHAOZUI
SPLIT_吵架.ANNOTSPLIT_CHAOJIA
SPLIT_告状.ANNOTSPLIT_GAOZHUANG
SPLIT_埋头.ANNOTSPLIT_MAITOU
SPLIT_增产.ANNOTSPLIT_ZENGCHAN
SPLIT_失业.ANNOTSPLIT_SHIYE
SPLIT_安心.ANNOTSPLIT_ANXIN
SPLIT_定性.ANNOTSPLIT_DINGXING
SPLIT_宣誓.ANNOTSPLIT_XUANSHI
SPLIT_对头.ANNOTSPLIT_DUITOU
SPLIT_就业.ANNOTSPLIT_JIUYE
SPLIT_帮忙.ANNOTSPLIT_BANGMANG
SPLIT_干杯.ANNOTSPLIT_GANBEI
SPLIT_幽默.ANNOTSPLIT_YOUMO
SPLIT_延期.ANNOTSPLIT_YANQI
SPLIT_开幕.ANNOTSPLIT_KAIMU
SPLIT_开课.ANNOTSPLIT_KAIKE
SPLIT_当面.ANNOTSPLIT_DANGMIAN
SPLIT_待业.ANNOTSPLIT_DAIYE
SPLIT_念书.ANNOTSPLIT_NIANSHU
SPLIT_懂事.ANNOTSPLIT_DONGSHI
SPLIT_成套.ANNOTSPLIT_CHENGTAO
SPLIT_打架.ANNOTSPLIT_DAJIA
SPLIT_打猎.ANNOTSPLIT_DALIE
SPLIT_打针.ANNOTSPLIT_DAZHEN
SPLIT_执勤.ANNOTSPLIT_ZHIQIN
SPLIT_执政.ANNOTSPLIT_ZHIZHENG
SPLIT_把关.ANNOTSPLIT_BAGUAN
SPLIT_投产.ANNOTSPLIT_TOUCHAN
SPLIT_投标.ANNOTSPLIT_TOUBIAO
SPLIT_投资.ANNOTSPLIT_TOUZI
SPLIT_报道.ANNOTSPLIT_BAODAO
SPLIT_拐弯.ANNOTSPLIT_GUAIWAN
SPLIT_招手.ANNOTSPLIT_ZHAOSHOU
SPLIT_招生.ANNOTSPLIT_ZHAOSHENG
SPLIT_拜年.ANNOTSPLIT_BAINIAN
SPLIT_挂号.ANNOTSPLIT_GUAHAO
SPLIT_捣蛋.ANNOTSPLIT_DAODAN
SPLIT_排队.ANNOTSPLIT_PAIDUI
SPLIT_接班.ANNOTSPLIT_JIEBAN
SPLIT_提名.ANNOTSPLIT_TIMING
SPLIT_提醒.ANNOTSPLIT_TIXING
SPLIT_搞鬼.ANNOTSPLIT_GAOGUI
SPLIT_摄影.ANNOTSPLIT_SHEYING
SPLIT_操心.ANNOTSPLIT_CAOXIN
SPLIT_放假.ANNOTSPLIT_FANGJIA
SPLIT_放手.ANNOTSPLIT_FANGSHOU
SPLIT_散步.ANNOTSPLIT_SANBU
SPLIT_敬礼.ANNOTSPLIT_JINGLI
SPLIT_施工.ANNOTSPLIT_SHIGONG
SPLIT_毕业.ANNOTSPLIT_BIYE
SPLIT_沾光.ANNOTSPLIT_ZHANGUANG
SPLIT_泄气.ANNOTSPLIT_XIEQI
SPLIT_注册.ANNOTSPLIT_ZHUCE
SPLIT_洗澡.ANNOTSPLIT_XIZAO
SPLIT_照相.ANNOTSPLIT_ZHAOXIANG
SPLIT_献身.ANNOTSPLIT_XIANSHEN
SPLIT_理发.ANNOTSPLIT_LIFA
SPLIT_生效.ANNOTSPLIT_SHENGXIAO
SPLIT_生气.ANNOTSPLIT_SHENGQI
SPLIT_用功.ANNOTSPLIT_YONGGONG
SPLIT_留意.ANNOTSPLIT_LIUYI
SPLIT_着急.ANNOTSPLIT_ZHEJI
SPLIT_睡觉.ANNOTSPLIT_SHUIJUE
SPLIT_矿工.ANNOTSPLIT_KUANGGONG
SPLIT_种地.ANNOTSPLIT_ZHONGDI
SPLIT_称心.ANNOTSPLIT_CHENGXIN
SPLIT_移民.ANNOTSPLIT_YIMIN
SPLIT_算数.ANNOTSPLIT_SUANSHU
SPLIT_纳闷.ANNOTSPLIT_NAMEN
SPLIT_结婚.ANNOTSPLIT_JIEHUN
SPLIT_结果.ANNOTSPLIT_JIEGUO
SPLIT_绝望.ANNOTSPLIT_JUEWANG
SPLIT_罢工.ANNOTSPLIT_BAGONG
SPLIT_致电.ANNOTSPLIT_ZHIDIAN
SPLIT_行军.ANNOTSPLIT_XINGJUN
SPLIT_行贿.ANNOTSPLIT_XINGHUI
SPLIT_见面.ANNOTSPLIT_JIANMIAN
SPLIT_请假.ANNOTSPLIT_QINGJIA
SPLIT_走路.ANNOTSPLIT_ZOULU
SPLIT_起哄.ANNOTSPLIT_QIHONG
SPLIT_起床.ANNOTSPLIT_QICHUANG
SPLIT_起草.ANNOTSPLIT_QICAO
SPLIT_起身.ANNOTSPLIT_QISHEN
SPLIT_跑步.ANNOTSPLIT_PAOBU
SPLIT_跳舞.ANNOTSPLIT_TIAOWU
SPLIT_辞职.ANNOTSPLIT_CIZHI
SPLIT_迎面.ANNOTSPLIT_YINGMIAN
SPLIT_还原.ANNOTSPLIT_HUANYUAN
SPLIT_违法.ANNOTSPLIT_WEIFA
SPLIT_送行.ANNOTSPLIT_SONGXING
SPLIT_造反.ANNOTSPLIT_ZAOFAN
SPLIT_遭殃.ANNOTSPLIT_ZAOYANG
SPLIT_配套.ANNOTSPLIT_PEITAO
SPLIT_闭幕.ANNOTSPLIT_BIMU
SPLIT_问好.ANNOTSPLIT_WENHAO
SPLIT_随便.ANNOTSPLIT_SUIBIAN
SPLIT_集资.ANNOTSPLIT_JIZI
SPLIT_集邮.ANNOTSPLIT_JIYOU
SPLIT_鞠躬.ANNOTSPLIT_JUGONG
SPLIT_鼓掌.ANNOTSPLIT_GUZHANG
TRANSFORM_化.ANNOTTRANSFORM_HUA
VB不VB.ANNOTVNOTV_BU
VB否VB.ANNOTVNOTV_FOU
VB没VB.ANNOTVNOTV_MEI

Danish

The morphological annotations are generated by the Danish POS Tagger and Morphological Analyzer input processor, which uses a machine learnt statistical model to tag every word in the user-input with exactly one tag from the OPEN NLP and Center for Sprogteknologi (CST) tag sets. It then maps these tags to the Teneo POS annotations like: NN.POS, VP.POS, PAST.POS, PRESENT.POS, etc.

The Danish Teneo NLU Ontology and Semantic Network distinguishes morphological ANNOT Language Objects between POS Language Objects, which are meant to capture part of speech such as verb and noun; and MST Language Objects, which are meant to capture morpho-syntactic traits such as noun number and verb tense.

The table below shows the morphological ANNOT Language Objects available in the Danish Teneo NLU Ontology and Semantic Network.

Morphological ANNOT language objectAnnotation(s) used as condition
POS_ADJ.ANNOTADJ.POS
POS_ADV.ANNOTADV.POS
POS_CARDINAL.ANNOTCARDINAL.POS
POS_FW.ANNOTCC.POS, CS.POS, DET.POS, INTERJ.POS, MISC.POS, PREP.POS, PRON.POS, POSS.POS
POS_INTERROG.ANNOTINTERROG.POS
POS_NOUN.ANNOTNN.POS
POS_ORDINAL.ANNOTORDINAL.POS
POS_PRONOUN.ANNOTPRON.POS
POS_PUNCTUATION.ANNOTPUNCT.POS, HYPHEN.POS
MST_ACTIVE.ANNOTACTIVE.POS
MST_COMPARATIVE.ANNOTCOMPARATIVE.POS
MST_DEFINITE.ANNOTDEF.POS
MST_INDEFINITE.ANNOTINDEF.POS
MST_INFINITIVE.ANNOTINF.POS
MST_MODAL.ANNOTMODAL.POS
MST_PARTICIPLE.ANNOTPARTICIPLE.POS
MST_PASSIVE.ANNOTPASSIVE.POS
MST_PAST.ANNOTPAST.POS
MST_PLURAL.ANNOTPL.POS
MST_POSITIVE.ANNOTPOSITIVE.POS
MST_POSSESSIVE.ANNOTPOSS.POS
MST_PRESENT.ANNOTPRESENT.POS
MST_PROPER.ANNOTPROPER.POS
MST_RELATIVE.ANNOTREL.POS
MST_SINGULAR.ANNOTSG.POS
MST_SUPERLATIVE.ANNOTSUPERLATIVE.POS
MST_SUPINE.ANNOTSUPINE.POS

Dutch

Morphological annotations are generated by the Dutch POS Tagger and Morphological Analyzer input processor, which uses a machine learnt statistical model to tag every word in the user-input with exactly one tag form the adaptation of the German STTS tag set. It then maps these tags to Teneo POS annotations like: NN.POS, VP.POS, PAST.POS, PRESENT.POS, etc.

The Dutch Teneo NLU Ontology and Semantic Network distinguishes morphological ANNOT Language Objects between POS Language Objects, which are meant to capture part of speech such as verb and noun; and MST Language Objects, which are meant to capture morpho-syntactic traits such as noun number or verb tense.

The table below gives an overview of the morphological ANNOT Language Objects implemented in the Dutch Lexical Resource.

ANNOT language objectAnnotation(s) used as condition
POS_ADJECTIVE.ANNOTADJ.POS
POS_ADVERB.ANNOTADV.POS
POS_CARDINAL.ANNOTCARDINAL.POS
POS_DETERMINER.ANNOTDET.POS
POS_FW.ANNOTCC.POS / CS.POS / DET.POS / INTERJ.POS / MISC.POS / PARTICLE.POS / PREP.POS / POST.POS
POS_INTERJECTION.ANNOTINTERJ.POS
POS_NOUN.ANNOTNN.POS
POS_PRONOUN.ANNOTPRON.POS
POS_PUNCTUATION.ANNOTPUNCT.POS
POS_TE.ANNOTTE.POS
POS_VERB.ANNOTVB.POS
POS_VERBPREFIX.ANNOTVBPREFIX.POS
MST_1STPERSON.ANNOT1STPERSON.POS
MST_2NDPERSON.ANNOT2NDPERSON.POS
MST_3RDPERSON.ANNOT3RDPERSON.POS
MST_ATTRIBUTIVE.ANNOTATTRIB.POS
MST_COMPARATIVE.ANNOTCOMPARATIVE.POS
MST_DEMONSTRATIVE.ANNOTDEMOS.POS
MST_FINITE.ANNOTFINITE.POS
MST_IMPERATIVE.ANNOTIMP.POS
MST_INDEFINITE.ANNOTINDEF.POS
MST_INFINITIVE.ANNOTINF.POS
MST_INTERROGATIVE.ANNOTINTERROG.POS
MST_MODAL.ANNOTMODAL.POS
MST_PARTICIPLE.ANNOTPARTICIPLE.POS
MST_PAST.ANNOTPAST.POS
MST_PERSONAL.ANNOTPERS.POS
MST_PLURAL.ANNOTPL.POS
MST_POSITIVE.ANNOTPOSITIVE.POS
MST_POSSESSIVE.ANNOTPOSS.POS
MST_PRESENT.ANNOTPRESENT.POS
MST_PROPER.ANNOTPROPER.POS
MST_RELATIVE.ANNOTREL.POS
MST_SINGULAR.ANNOTSG.POS
MST_SUBSTITUTIVE.ANNOTSUBST.POS
MST_SUPERLATIVE.ANNOTSUPERLATIVE.POS

Person and number annotations for verbs

The Dutch Part-of-Speech Tagger input processor also annotates morphological information about the person and the number for all finite verb forms in an additional rule-based step.

The corresponding Teneo POS annotations are presented in the below table.

PersonNumber
1STPERSON.POSSG.POS
2NDPERSON.POS 3RDPERSON.POSPL.POS

English

Morphological annotations are generated by the English POS Tagger and Morphological Analyzer input processor, which uses a machine learnt statistical model to tag every word in the user-input with exactly one tag from the Penn Treebank tag set. It then maps these tags to Teneo POS annotations like NN.POS, VP.POS, PAST.POS, PRESENT.POS, etc.

The English Teneo NLU Ontology and Semantic Network distinguishes morphological ANNOT Language Objects between POS Language Objects, which are meant to capture part of speech such as verb and noun; and MST Language Objects, which are meant to capture morpho-syntactic traits such as noun number and verb tense.

The table below gives an overview of the morphological ANNOT Language Objects available in the English Teneo NLU Ontology and Semantic Network.

Morphological ANNOT language objectAnnotation(s) used as condition
POS_ADJECTIVE.ANNOTADJ.POS
POS_ADVERB.ANNOTADV.POS
POS_BRACKET.ANNOTBRACKET.POS
POS_CARDINAL.ANNOTCARDINAL.POS
POS_INTERJECTION.ANNOTINTERJ.POS
POS_NOUN.ANNOTNN.POS
POS_POSSESSIVE.ANNOTPOSS.POS
POS_PRONOUN.ANNOTPRON.POS
POS_PUNCTUATION.ANNOTPUNCT.POS
POS_VERB.ANNOTVB.POS
POS_INTERROG.ANNOTINTERROG.POS
POS_FW.ANNOTCC.POS / DET.POS / EX.POS / FOREIGN.POS / PREP.POS / LS.POS / PREDET.POS / PARTICLE.POS / SYM.POS / INTERJ.POS / POSS.POS
MST_3RDPERSON.ANNOT3RDPERSON.POS
MST_COMPARATIVE.ANNOTCOMP.POS
MST_GERUND.ANNOTGERUND.POS
MST_INFINITIVE.ANNOTINF.POS
MST_MODAL.ANNOTMODAL.POS
MST_PARTICIPLE.ANNOTPARTICIPLE.POS
MST_PAST.ANNOTPAST.POS
MST_PERSONAL.ANNOTPERS.POS
MST_PLURAL.ANNOTPL.POS
MST_PRESENT.ANNOTPRESENT.POS
MST_PROPER.ANNOTPROPER.POS
MST_SINGULAR.ANNOTSG.POS
MST_SUPERLATIVE.ANNOTSUPER.POS

French

Morphological annotations are generated by the French POS Tagger and Morphological Analyzer input processor, which uses a machine learnt statistical model to tag every word in the user-input with exactly one tag from the French Treebank tag set. It then maps these tags to Teneo POS annotations like: NN.POS, VP.POS, PAST.POS, PRESENT.POS, etc.

The French Teneo NLU Ontology and Semantic Network distinguishes morphological ANNOT Language Objects between POS Language Objects, which are meant to capture part of speech such as verb and noun; and MST Language Objects, which are meant to capture morpho-syntactic traits such as noun number or verb tense.

The table below gives an overview of the morphological ANNOT Language Objects available in the French Teneo NLU Ontology and Semantic Network.

Morphological ANNOT language objectAnnotation(s) used as condition
POS_ADJECTIVE.ANNOTADJ.POS
POS_ADVERB.ANNOTADV.POS
POS_CARDINAL.ANNOTCARDINAL.POS
POS_FOREIGN.ANNOTFOREIGN.POS
POS_INTERJECTION.ANNOTINTERJ.POS
POS_NOUN.ANNOTNN.POS
POS_PREFIX.ANNOTPREFIX.POS
POS_PRONOUN.ANNOTPRON.POS
POS_PUNCTUATION.ANNOTPUNCT.POS
POS_VERB.ANNOTVB.POS
POS_FW.ANNOTCC.POS / CS.POS / DET.POS / INTERJ.POS / MISC.POS / PREP.POS
MST_1STPERSON.ANNOT1STPERSON.POS
MST_2NDPERSON.ANNOT2NDPERSON.POS
MST_3RDPERSON.ANNOT3RDPERSON.POS
MST_CLITIC.ANNOTCLITIC.POS
MST_CONDITIONAL.ANNOTCONDITIONAL.POS
MST_DEMONSTRATIVE.ANNOTDEMOS.POS
MST_EXCLAMATIVE.ANNOTEXCLAM.POS
MST_FUTURE.ANNOTFUTURE.POS
MST_IMPERATIVE.ANNOTIMP.POS
MST_IMPERFECT.ANNOTIMPERFECT.POS
MST_INDEFINITE.ANNOTINDEF.POS
MST_INDICATIVE.ANNOTINDICATIVE.POS
MST_INFINITIVE.ANNOTINF.POS
MST_INTERROGATIVE.ANNOTINTERROG.POS
MST_MODAL.ANNOTMODAL.POS
MST_NEGATION.ANNOTNEGATION.POS
MST_ORDINAL.ANNOTORDINAL.POS
MST_PARTICIPLE.ANNOTPARTICIPLE.POS
MST_PAST.ANNOTPERFECT.POS / IMPERFECT.POS / PARTICIPLE.POS
MST_PERFECT.ANNOTPERFECT.POS
MST_PERSONAL.ANNOTPERS.POS
MST_PLURAL.ANNOTPL.POS
MST_POSSESSIVE.ANNOTPOSS.POS
MST_PRESENT.ANNOTPRESENT.POS
MST_PROPER.ANNOTPROPER.POS
MST_RELATIVE.ANNOTREL.POS
MST_SINGULAR.ANNOTSG.POS
MST_SUBJUNCTIVE.ANNOTSUBJUNCTIVE.POS

German

Morphological annotations are generated by the German POS Tagger and Morphological Analyzer input processor, which is a hybrid input processor that is first using a machine learnt statistical model to tag every word in the user-input with exactly one tag from an extended version of the STTS tag set. It then maps these tags to Teneo POS annotations like NN.POS, VP.POS, PAST.POS, PRESENT.POS, etc.

After mapping the tags to Teneo annotations, the German POS Tagger and Morphological Analyzer input processor uses this information and some cleverly designed rules to further distinguish the person, i.e. 1STPERSON.POS, 2NDPERSON.POS or 3RDPERSON.POS, and the number, i.e. SG.POS or PL.POS, for every verb in the user input, thus providing the complete range of morphological information to the user. For imperatives (VVIMP), only information about the number is annotation. For ambiguous cases like Kommen Sie mit! both SG.POS and PL.POS are annotated.

The German Teneo NLU Ontology and Semantic Network distinguishes morphological ANNOT Language Objects between POS Language Objects, which are meant to capture part of speech such as verb and noun; and MST Language Objects, which are meant to capture morpho-syntactic morpho-syntactic traits such as number or verb tense.

The table below gives and overview of the morphological ANNOT Language Objects available in the German Teneo NLU Ontology and Semantic Network.

Morphological ANNOT language objectAnnotation(s) used as conditionNotes
POS_ADJECTIVE.ANNOTADJ.POSMatches with all forms of adjectives, i.e. attributive an predicative forms as well as adjectives that are used adverbially (as in “Er rennt schnell”). Additionally, past participles that act as an adjective (as in “Das vermisste Kind”) and all present participles are annotated as adjectives.
POS_ADPOSITION.ANNOTADPOSITION.POSMatches with prepositions, postpositions and circum-positions.
POS_ADVERB.ANNOTADV.POSMatches with pure adverbs, i.e. adverbs that are not directly derived from adjectives.
POS_CARDINAL.ANNOTCARDINAL.POS
POS_CONJUNCTION.ANNOTCC.POS / CS.POSMatches with coordinating as well as subordinating conjunctions.
POS_DETERMINER.ANNOTDET.POSMatches with definite and indefinite articles as well as demonstrative pronouns.
POS_FW.ANNOTADPOSITION.POS / CC.POS / CS.POS / DET.POS / PARTICLE.POS / INTERJ.POS / POSS.POS / TRUNC.POS / XY.POS
POS_INTERJECTION.ANNOTINTERJ.POS
POS_NOUN.ANNOTNN.POSMatches with normal nouns and proper nouns.
POS_PRONOUN.ANNOTPRON.POS
POS_PUNCTUATION.ANNOTPUNCT.POS
POS_VERB.ANNOTVB.POS
POS_VERBPREFIX.ANNOTVBPREFIX.POSMatches with a verb prefix that is separated from the rest of the verb (as in “Der Zug kommt um vier Uhr an”).
POS_ZU.ANNOTZU.POSMatches with “zu” if it is used with an infinitive (as in “Ich freue mich hier zu sein”). Other forms of “zu” are annotated as prepositions (as in “Er kommt zu mir”) or as adverbs in combination with adjectives (as in “Das ist zu teuer”).
MST_1STPERSON.ANNOT1STPERSON.POS
MST_2NDPERSON.ANNOT2NDPERSON.POS
MST_3RDPERSON.ANNOT3RDPERSON.POS
MST_ATTRIBUTIVE.ANNOTATTRIB.POSOnly used together with interrogative pronouns that are used attributively (as in “Welche Farbe willst du?” as opposed to substituting interrogative pronouns (as in “Welche willst du?).
MST_COMPARATIVE.ANNOTCOMPARATIVE.POS
MST_FINITE.ANNOTFINITE.POS
MST_INDEFINITE.ANNOTINDEF.POS
MST_INFINITIVE.ANNOTINF.POS
MST_IMPERATIVE.ANNOTIMP.POS
MST_INTERROGATIVE.ANNOTINTERROG.POS
MST_MODAL.ANNOTMODAL.POSMatches exclusively with any form of the verbs “können”, “müssen”, “dürfen”, “wollen”, “sollen” or “mögen” regardless whether they are used together with an infinitive in the context.
MST_PARTICIPLE.ANNOTPARTICIPLE.POSOnly matches with past participles. Present participles are annotated as adjectives.
MST_PAST.ANNOTPAST.POS
MST_PERSONAL.ANNOTPERS.POS
MST_PLURAL.ANNOTPL.POS
MST_POSITIVE.ANNOTPOSITIVE.POS
MST_POSSESSIVE.ANNOTPOSS.POS
MST_PRESENT.ANNOTPRESENT.POS
MST_PROPER.ANNOTPROPER.POS
MST_RELATIVE.ANNOTREL.POS
MST_SINGULAR.ANNOTSG.POS
MST_SUBSITITUTIVE.ANNOTSUBST.POSOnly used together with interrogative pronouns that are used substitutively (as in “Welche willst du?”) as opposed to attributive interrogative pronouns (as in “Welche Farbe willst du?).
MST_SUPERLATIVE.ANNOTSUPERLATIVE.POS

Italian

Morphological annotations are generated by the Italian POS Tagger and Morphological Analyzer input processor, which uses a machine learnt statistical model to tag every word in the user-input with exactly one tag from the modified TANL tag set. In the final tag set that was used to train the Italian POS Tagger, the tag set for main verbs (V) and those for auxiliary verbs (VA) were merged, and the tags for all determiners (DD, DE, DI, DQ, DR), the pre-determiner tag (T) and the tags for articles (RI, RD) were merged into one single DET tag. The input processor next maps these tags to Teneo POS annotations like: NN.POS, VP.POS, PAST.POS, PRESENT.POS, etc.

The Italian Teneo NLU Ontology and Semantic Network distinguishes morphological ANNOT Language Objects, which are meant to capture part of speech such as verb and noun; and MST Language Objects, which are meant to capture morpho-syntactic traits such as noun number and verb tense.

The table below gives an overview of the morphological ANNOT Language Objects available in the Italian Teneo NLU Ontology and Semantic Network.

Morphological ANNOT language objectAnnotation(s) used as condition
POS_ABBREVIATION.ANNOTABBREV.POS
POS_ADJECTIVE.ANNOTADJ.POS
POS_ADVERB.ANNOTADV.POS
POS_CARDINAL.ANNOTCARDINAL.POS
POS_FOREIGN.ANNOTFOREIGN.POS
POS_INTERJECTION.ANNOTINTERJ.POS
POS_NOUN.ANNOTNN.POS
POS_ORDINAL.ANNOTORDINAL.POS
POS_PRONOUN.ANNOTPRON.POS
POS_PUNCTUATION.ANNOTPUNCT.POS
POS_HASHTAG.ANNOTHASHTAG.POS
POS_ATMENTION.ANNOTATMENTION.POS
POS_EMOTICON.ANNOTEMOTICON.POS
POS_VERB.ANNOTVB.POS
POS_FW.ANNOTCC.POS / CS.POS / DET.POS / INTERJ.POS / MISC.POS / PREP.POS
MST_3RDPERSON.ANNOT3RDPERSON.POS
MST_CLITIC.ANNOTCLITIC.POS
MST_CONDITIONAL.ANNOTCONDITIONAL.POS
MST_DEMONSTRATIVE.ANNOTDEMOS.POS
MST_FUTURE.ANNOTFUTURE.POS
MST_GERUND.ANNOTGERUND.POS
MST_INDEFINITE.ANNOTINDEF.POS
MST_INDICATIVE.ANNOTINDICATIVE.POS
MST_INFINITIVE.ANNOTINF.POS
MST_IMPERATIVE.ANNOTIMP.POS
MST_IMPERFECT.ANNOTIMPERFECT.POS
MST_INTERROGATIVE.ANNOTINTERROG.POS
MST_MODAL.ANNOTMODAL.POS
MST_NEGATION.ANNOTNEGATION.POS
MST_PARTICIPLE.ANNOTPARTICIPLE.POS
MST_PAST.ANNOTPERFECT.POS / IMPERFECT.POS / PARTICIPLE.POS
MST_PERFECT.ANNOTPERFECT.POS
MST_PERSONAL.ANNOTPERS.POS
MST_PLURAL.ANNOTPL.POS
MST_POSSESSIVE.ANNOTPOSS.POS
MST_PRESENT.ANNOTPRESENT.POS
MST_PROPER.ANNOTPROPER.POS
MST_RELATIVE.ANNOTREL.POS
MST_SINGULAR.ANNOTSG.POS
MST_SUBJUNCTIVE.ANNOTSUBJUNCTIVE.POS

Japanese

The Japanese Annotator input processor uses a state-of-the-art tokenizer and morphological analyzer to split the user inputs into tokens and annotate them with morphological and syntactic information.

The table below gives an overview of the morphological ANNOT Language Objects available in the Japanese Teneo NLU Ontology and Semantic Network.

Morphological ANNOT language objectAnnotation used as condition
POS_ADJECTIVE.ANNOTADJ.POS
POS_ADVERB.ANNOTADV.POS
POS_CARDINAL.ANNOTCARDINAL.POS
POS_CONJUNCTION.ANNOTCONJ.POS
POS_COPULA.POSCOPULA.POS
POS_COUNTER.ANNOTCOUNTER.POS
POS_DETERMINER.ANNOTDET.POS
POS_FW.ANNOTFW.POS
POS_INTERJECTION.ANNOTINTERJ.POS
POS_NOUN.ANNOTNN.POS
POS_PARTICLE.ANNOTPARTICLE.POS
POS_PREFIX.POSPREFIX.POS
POS_PREPOSITION.ANNOTPREP.POS
POS_PRONOUN.ANNOTPRON.POS
POS_PROPER.ANNOTPROPER.POS
POS_SUFFIX.ANNOTSUFFIX.POS
POS_SYMBOL.ANNOTSYM.POS
POS_VERB.ANNOTVB.POS
MST_ALMOST.ANNOTALMOST.MST
MST_ASSUMPTION.ANNOTASSUMPTION.MST
MST_CAUSATIVE.ANNOTCAUSATIVE.MST
MST_だす.ANNOTDASU.MST
MST_DESIRE.ANNOTDESIRE.MST
MST_EXCESS.ANNOTEXCESS.MST
MST_FORMAL.ANNOTFORMAL.MST
MST_がる.ANNOTGARU.MST
MST_GERUND.ANNOTGERUND.MST
MST_はじめる.ANNOTHAJIMERU.MST
MST_IMPERATIVE.ANNOTIMPERATIVE.MST
MST_ITERATIVE.ANNOTITERATIVE.MST
MST_かねる.ANNOTKANERU.MST
MST_きる.ANNOTKIRU.MST
MST_NEGATION.ANNOTNEGATION.MST
MST_おえる.ANNOTOERU.MST
MST_おわる.ANNOTOWARU.MST
MST_PASSIVE.ANNOTPASSIVE.MST
MST_PAST.ANNOTPAST.MST
MST_PROGRESSIVE.ANNOTPROGRESSIVE.MST
MST_連用形.ANNOTRENYOKEI.MST
MST_てあげる.ANNOTTEAGERU.MST
MST_ていく.ANNOTTEIKU.MST
MST_ていただく.ANNOTTEITADAKU.MST
MST_てくださる.ANNOTTEKUDASARU.MST
MST_てくれる.ANNOTTEKURERU.MST
MST_てみる.ANNOTTEMIRU.MST
MST_てもらう.ANNOTTEMORAU.MST
MST_ておく.ANNOTTEOKU.MST
MST_てしまう.ANNOTTESHIMAU.MST
MST_てやる.ANNOTTEYARU.MST
MST_VOLITION.ANNOTVOLITION.MST
MST_やがる.ANNOTYAGARU.MST
MST_NONNEG.ANNOTNONNEG.MST
MST_NONPAST.ANNOTNONPAST.MST

Spanish

Morphological annotations are generated by the Spanish POS Tagger and Morphological Analyzer input processor, which uses a machine learnt statistical model to tag every word in the user-input with exactly one tag from the EAGLES Guidelines tag set. It then maps these tags to Teneo POS annotations like: NN.POS, VP.POS, PAST.POS, PRESENT.POS, etc.

The Spanish Teneo NLU Ontology and Semantic Network distinguishes morphological ANNOT Language Objects between POS Language Objects, which are meant to capture part of speech such as verb and noun; and MST Language Objects, which are meant to capture morpho-syntactic traits such as noun number and verb tense.

The table below gives an overview of the morphological ANNOT Language Objects available in the Spanish Teneo NLU Ontology and Semantic Network.

Morphological ANNOT language objectAnnotation(s) used as condition
POS_ABBREVIATION.ANNOTABBREV.POS
POS_ADJECTIVE.ANNOTADJ.POS
POS_ADVERB.ANNOTADV.POS
POS_CARDINAL.ANNOTCARDINAL.POS
POS_FOREIGN.ANNOTFOREIGN.POS
POS_INTERJECTION.ANNOTINTERJ.POS
POS_NOUN.ANNOTNN.POS
POS_ORDINAL.ANNOTORDINAL.POS
POS_PRONOUN.ANNOTPRON.POS
POS_PUNCTUATION.ANNOTPUNCT.POS
POS_VERB.ANNOTVB.POS
POS_FW.ANNOTCC.POS / CS.POS / DET.POS / INTERJ.POS / MISC.POS / PREP.POS
MST_1STPERSON.ANNOT1STPERSON.POS
MST_2NDPERSON.ANNOT2NDPERSON.POS
MST_3RDPERSON.ANNOT3RDPERSON.POS
MST_CLITIC.ANNOTCLITIC.POS
MST_CONDITIONAL.ANNOTCONDITIONAL.POS
MST_DEMONSTRATIVE.ANNOTDEMOS.POS
MST_FUTURE.ANNOTFUTURE.POS
MST_GERUND.ANNOTGERUND.POS
MST_IMPERATIVE.ANNOTIMP.POS
MST_IMPERFECT.ANNOTIMPERFECT.POS
MST_INDEFINITE.ANNOTINDEF.POS
MST_INDICATIVE.ANNOTINDICATIVE.POS
MST_INFINITIVE.ANNOTINF.POS
MST_INTERROGATIVE.ANNOTINTERROG.POS
MST_MODAL.ANNOTMODAL.POS
MST_NEGATION.ANNOTNEGATION.POS
MST_PARTICIPLE.ANNOTPARTICIPLE.POS
MST_PAST.ANNOTPERFECT.POS / IMPERFECT.POS / PARTICIPLE.POS
MST_PERFECT.ANNOTPERFECT.POS
MST_PERSONAL.ANNOTPERS.POS
MST_PLURAL.ANNOTPL.POS
MST_POSSESSIVE.ANNOTPOSS.POS
MST_PRESENT.ANNOTPRESENT.POS
MST_PROPER.ANNOTPROPER.POS
MST_RELATIVE.ANNOTREL.POS
MST_SINGULAR.ANNOTSG.POS
MST_SUBJUNCTIVE.ANNOTSUBJUNCTIVE.POS

Swedish

Morphological annotations are generated by the Swedish POS Tagger and Morphological Analyzer input processor, which uses a machine learnt statistical model to tag every word in the user-input with exactly one tag from the Stockholm-Umeå corpus tag set. It then maps these tags to Teneo POS annotations like: NN.POS, VP.POS, PAST.POS, PRESENT.POS, etc.

The Swedish Teneo NLU Ontology and Semantic Network distinguishes morphological ANNOT Language Objects between POS Language Objects, which are meant to capture part of speech such as verb and noun; and MST Language Objects, which are meant to capture morpho-syntactic traits such as noun number or verb tense.

The table below gives an overview of the morphological ANNOT Language Objects available in the Swedish Teneo NLU Ontology and Semantic Network.

Morphological ANNOT language objectAnnotation(s) used as condition
POS_ADJ.ANNOTADJ.POS
POS_ADV.ANNOTADV.POS
POS_CARDINAL.ANNOTCARDINAL.POS
POS_FOREIGN.ANNOTFOREIGN.POS
POS_FW.ANNOTCC.POS, CS.POS, DET.POS, INTERJ.POS, MISC.POS, PREP.POS, PARTICLE.POS, POSS.POS
POS_INTERROG.ANNOTINTERROG.POS
POS_NOUN.ANNOTNN.POS
POS_ORDINAL.ANNOTORDINAL.POS
POS_PRONOUN.ANNOTPRON.POS
POS_PUNCTUATION.ANNOTPUNCT.POS, HYPHEN.POS
POS_VERB.ANNOTVB.POS
MST_ACTIVE.ANNOTACTIVE.POS
MST_COMPARATIVE.ANNOTCOMPARATIVE.POS
MST_DEFINITE.ANNOTDEF.POS
MST_INDEFINITE.ANNOTINDEF.POS
MST_INFINITIVE.ANNOTINF.POS
MST_MODAL.ANNOTMODAL.POS
MST_PARTICIPLE.ANNOTPARTICIPLE.POS
MST_PASSIVE.ANNOTPASSIVE.POS
MST_PAST.ANNOTPAST.POS
MST_PERSONAL.ANNOTPERS.POS
MST_PLURAL.ANNOTPL.POS
MST_POSITIVE.ANNOTPOSITIVE.POS
MST_POSSESSIVE.ANNOTPOSS.POS
MST_PRESENT.ANNOTPRESENT.POS
MST_PROPER.ANNOTPROPER.POS
MST_RELATIVE.ANNOTREL.POS
MST_SINGULAR.ANNOTSG.POS
MST_SUPERLATIVE.ANNOTSUPERLATIVE.POS
MST_SUPINE.ANNOTSUPINE.POS

Turkish

The Turkish Analyzer input processor uses a state-of-the-art tokenizer and morphological analyzer to split the user inputs into tokens and annotate them with morphological and syntactic information.

The table below gives an overview of the morphological ANNOT Language Objects available in the Turkish Teneo NLU Ontology and Semantic Network.

Morphological ANNOT language objectAnnotation used as condition
POS_ADJECTIVE.ANNOTADJ.POS
POS_ADVERB.ANNOTADV.POS
POS_CARDINAL.ANNOTCARDINAL.POS
POS_CONJUNCTION.ANNOTCC.POS
POS_DETERMINER.ANNOTDET.POS
POS_DUPLICATOR.ANNOTDUPLICATOR.POS
POS_INTERJECTION.ANNOTINTERJ.POS
POS_INTERROG.ANNOTINTERROG.POS
POS_NOUN.ANNOTNN.POS
POS_NUMERAL.ANNOTNUMERAL.POS
POS_ORDINAL.ANNOTORDINAL.POS
POS_POST_POSITIVE.ANNOTPOST_POSITIVE.POS
POS_PRONOUN.ANNOTPRON.POS
POS_PUNCTUATION.ANNOTPUNCT.POS
POS_VERB.ANNOTVERB.POS
MST_1STPERSON.ANNOT1STPERSON.MST
MST_2NDPERSON.ANNOT2NDPERSON.MST
MST_3RDPERSON.ANNOT3RDPERSON.MST
MST_ABILITY.ANNOTABILITY.MST
MST_ABLATIVE.ANNOTABLATIVE.MST
MST_ACCUSATIVE.ANNOTACCUSATIVE.MST
MST_ACQUIRE.ANNOTACQUIRE.MST
MST_ACT_OF.ANNOTACT_OF.MST
MST_ADAMANTLY.ANNOTADAMANTLY.MST
MST_ADJECTIVE.ANNOTADJECTIVE.MST
MST_ADVERB.ANNOTADVERB.MST
MST_AFTER_DOING_SO.ANNOTAFTER_DOING_SO.MST
MST_AGENTIVE.ANNOTAGENTIVE.MST
MST_ALMOST.ANNOTALMOST.MST
MST_AORIST.ANNOTAORIST.MST
MST_AS_IF.ANNOTAS_IF.MST
MST_AS_LONG_AS.ANNOTAS_LONG_AS.MST
MST_BECOME.ANNOTBECOME.MST
MST_BY_DOING_SO.ANNOTBY_DOING_SO.MST
MST_CAUSATIVE.ANNOTCAUSATIVE.MST
MST_CONDITION.ANNOTCONDITION.MST
MST_CONJUNCTION.ANNOTCONJUNCTION.MST
MST_COP.ANNOTCOP.MST
MST_DATIVE.ANNOTDATIVE.MST
MST_DEMONSTRATIVE.ANNOTDEMONSTRATIVE.MST
MST_DESIRE.ANNOTDESIRE.MST
MST_DETERMINER.ANNOTDETERMINER.MST
MST_DIMINUTIVE.ANNOTDIMINUTIVE.MST
MST_DUPLICATOR.ANNOTDUPLICATOR.MST
MST_EQUATIVE.ANNOTEQUATIVE.MST
MST_EVER_SINCE.ANNOTEVER_SINCE.MST
MST_FEEL_LIKE.ANNOTFEEL_LIKE.MST
MST_FUTURE.ANNOTFUTURE.MST
MST_GENITIVE.ANNOTGENITIVE.MST
MST_HASTILY.ANNOTHASTILY.MST
MST_IMPERATIVE.ANNOTIMPERATIVE.MST
MST_INFINITIVE1.ANNOTINFINITIVE1.MST
MST_INFINITIVE2.ANNOTINFINITIVE2.MST
MST_INFINITIVE3.ANNOTINFINITIVE3.MST
MST_INFORMAL.ANNOTINFORMAL.MST
MST_INSTRUMENTAL.ANNOTINSTRUMENTAL.MST
MST_INTERJECTION.ANNOTINTERJECTION.MST
MST_INTERROG.ANNOTINTERROG.MST
MST_JUST_LIKE.ANNOTJUST_LIKE.MST
MST_LOCATIVE.ANNOTLOCATIVE.MST
MST_LY.ANNOTLY.MST
MST_NARRATIVE.ANNOTNARRATIVE.MST
MST_NECESSITY.ANNOTNECESSITY.MST
MST_NEGATIVE.ANNOTNEGATIVE.MST
MST_NESS.ANNOTNESS.MST
MST_NO_POSESSION.ANNOTNO_POSESSION.MST
MST_NOMINATIVE.ANNOTNOMINATIVE.MST
MST_NOT_STATE.ANNOTNOT_STATE.MST
MST_NOUN.ANNOTNOUN.MST
MST_NUMERAL.ANNOTNUMERAL.MST
MST_OPTATIVE.ANNOTOPTATIVE.MST
MST_PARTICIPLE.ANNOTPARTICIPLE.MST
MST_PASSIVE.ANNOTPASSIVE.MST
MST_PAST.ANNOTPAST.MST
MST_PERSONAL.ANNOTPERSONAL.MST
MST_PLURAL.ANNOTPLURAL.MST
MST_POSSESSIVE.ANNOTPOSSESSIVE.MST
MST_POST_POSITIVE.ANNOTPOST_POSITIVE.MST
MST_PRESENT.ANNOTPRESENT.MST
MST_PROGRESSIVE1.ANNOTPROGRESSIVE1.MST
MST_PROGRESSIVE2.ANNOTPROGRESSIVE2.MST
MST_PRONOUN.ANNOTPRONOUN.MST
MST_PROPER.ANNOTPROPER.MST
MST_PUNCTUATION.ANNOTPUNCTUATION.MST
MST_QUANTITATIVE.ANNOTQUANTITATIVE.MST