Скачать презентацию How Net and Computation of Meaning Zhendong Dong Скачать презентацию How Net and Computation of Meaning Zhendong Dong

1e6b863f689d43067b9d6daaf0025cea.ppt

  • Количество слайдов: 42

How. Net and Computation of Meaning Zhendong Dong dzd@keenage. com WWW. keenage. com GWC-06 How. Net and Computation of Meaning Zhendong Dong [email protected] com WWW. keenage. com GWC-06 Jeju, Korea 2006 -01 -22

Outlines n Bird’s-eye view of How. Net n Prominent features Outlines n Bird’s-eye view of How. Net n Prominent features

Bird’s-eye view of How. Net What is How. Net? n History of How. Net Bird’s-eye view of How. Net What is How. Net? n History of How. Net n Statistics on latest version n Composition of How. Net n

What is How. Net? n n How. Net is an on-line extralinguistic knowledge system What is How. Net? n n How. Net is an on-line extralinguistic knowledge system for the computation of meaning in HLT. How. Net unveils inter-concept relations and inter-attribute relations of the concepts as connoted in its Chinese. English lexicon.

History of How. Net 1988 Basic research started 19991 st version released 2000 Revision History of How. Net 1988 Basic research started 19991 st version released 2000 Revision of KDML started 2002 New version released

Statistics - general Chinese word & expression English word & expression Chinese meaning English Statistics - general Chinese word & expression English word & expression Chinese meaning English meaning Definition Record 84102 80250 98530 100071 25295 161743

A record in How. Net dictionary NO. =076856 W_C=买主 G_C=N [mai 3 zhu 3] A record in How. Net dictionary NO. =076856 W_C=买主 G_C=N [mai 3 zhu 3] E_C= W_E=buyer G_E=N E_E= DEF={human|人: domain={commerce|商业}, {buy|买: agent={~}}}

Statistics - semantic Thing Component Time Space Attribute Atttibute-value Event Chinese 58153 7025 2238 Statistics - semantic Thing Component Time Space Attribute Atttibute-value Event Chinese 58153 7025 2238 1071 3776 9089 12634 English 58096 7023 2244 1071 4045 8478 10076

Statistics – main syntactic categories ADJ ADV VERB NOUN PRON NUM PREP AUX CLA Statistics – main syntactic categories ADJ ADV VERB NOUN PRON NUM PREP AUX CLA Chinese 11705 1516 25929 46867 112 225 128 77 424 English 9576 2084 21017 48342 71 242 113 49 0

Statistics – part of relations Chinese synset: Set = 13463 Word Form = 54312 Statistics – part of relations Chinese synset: Set = 13463 Word Form = 54312 antonym: Set = 12777 converse: Set = 6753 English synset: Set = 18575 Word Form = 58488 antonym: Set = 12032 converse: Set = 6442

Composition Database n Tools for computation of meaning n Composition Database n Tools for computation of meaning n

Database Dictionary n Taxonomies n Axiomatic relations & role shifting n Database Dictionary n Taxonomies n Axiomatic relations & role shifting n

Dictionary Dictionary

Taxonomies - 10 § § § § § Entity Event Attribute. Value Secondary features Taxonomies - 10 § § § § § Entity Event Attribute. Value Secondary features Event roles Typical actors of event roles Event relations and role shifting Antonymous sememe pairs Converse sememe pairs

Tools for computation of meaning Browser n Secondary resources n Tools for computation of meaning Browser n Secondary resources n

Prominent features n n n All syntactic classes of words included Sememes and semantic Prominent features n n n All syntactic classes of words included Sememes and semantic roles Defining concepts in KDML on the basis of sememes and semantic roles Relations – the soul of How. Net Relations obtained by computing rather than manually-coding Identical representation in various linguistic structures

Sememes Entity thing (physical, mental, fact) component (part, fitting) time space (direction, location) Event Sememes Entity thing (physical, mental, fact) component (part, fitting) time space (direction, location) Event (relation, state; action) Attribute. Value Secondary feature 2099 151 812 247 889 121

Semantic roles 91 (1) Main semantic roles (a) principal semantic roles: 6 (b) affected Semantic roles 91 (1) Main semantic roles (a) principal semantic roles: 6 (b) affected semantic roles: 11 (2) peripheral semantic roles (a) time: 12 (f) basis: 6 (b) space: 11 (g) comparison: 2 (c) resultant: 8 (h) coordination: 6 (d) manner: 11 (i) commentary: 2 (e) modifier: 16

Defining concepts (1) W_E=doctor G_E=V DEF={doctor|医治} W_E=doctor G_E=N DEF={human|人: Host. Of={Occupation|职位}, domain={medical|医}, {doctor|医治: agent={~}}} Defining concepts (1) W_E=doctor G_E=V DEF={doctor|医治} W_E=doctor G_E=N DEF={human|人: Host. Of={Occupation|职位}, domain={medical|医}, {doctor|医治: agent={~}}} W_E=doctor G_E=N E_E= DEF={human|人: {own|有: possession={Status|身分: domain={education|教育}, modifier={High. Rank|高等: degree={most|最}}}, possessor={~}}}

Defining concepts (2) W_E=buy G_E=V DEF={buy|买} cf. (Word. Net) obtain by purchase; acquire by Defining concepts (2) W_E=buy G_E=V DEF={buy|买} cf. (Word. Net) obtain by purchase; acquire by means of finacial transaction W_E=buy G_E=V DEF={Give. As. Gift|赠: manner={guilty|有罪}, purpose={entice|勾引}} cf. (Word. Net) make illegal payments to in exchange for favors or influence

Relations – the soul of How. Net Meaning is represented by relations n Computation Relations – the soul of How. Net Meaning is represented by relations n Computation of meaning is based on relations n

1. Event Frame ~ Verb frame - {event|事件} ├ {static|静态} {event|事件} │ ├ {relation|关系} 1. Event Frame ~ Verb frame - {event|事件} ├ {static|静态} {event|事件} │ ├ {relation|关系} {static|静态} │ │ ├ {possession|领属关系} {relation|关系} │ │ │ ├ {own|有} {possession|领属关系: possessor={*}, possession={*}} │ │ ├ {obtain|得到} {own|有: possessor={*}, possession={*}, source={*}} └ {act|行动} {event|事件: agent={*}} ├ {Act. General|泛动} {act|行动: agent={*}} └ {Act. Specific|实动} {act|行动: agent={*}} └ {Alter. Specific|实变} {Act. Specific|实动: agent={*}} ├ {Alter. Relation|变关系} {Alter. Specific|实变: agent={*}} │ ├ {Alter. Possession|变领属} {Alter. Relation|变关系: agent={*}, possession={*}} │ │ ├ {take|取} {Alter. Possession|变领属: agent={*}, possession={*}, source={*}} │ │ │ ├ {buy|买} {take|取: agent={*}, possession={*}, source={*}, cost={*}, beneficiary={*}

2. Typical actors of event roles ~ Verb. Net │ ├ {buy|买} {take|取: agent={human|人}{group|群体->}, 2. Typical actors of event roles ~ Verb. Net │ ├ {buy|买} {take|取: agent={human|人}{group|群体->}, possession={artifact|人 物->}, source={human|人}{Institute. Place|场所}, cost={money|货币}, beneficiary={human|人}{group|群体->}, domain={economy|经济}}

Axiomatic Relations & Role Shifting - 1 {buy|买} <----> {obtain|得到} [consequence]; agent OF {buy|买}=possessor Axiomatic Relations & Role Shifting - 1 {buy|买} <----> {obtain|得到} [consequence]; agent OF {buy|买}=possessor OF {obtain|得到}; possession OF {buy|买}=possession OF {obtain|得到}. {buy|买} <----> {obtain|得到} [consequence]; beneficiary OF {buy|买}=possessor OF {obtain|得到}; possession OF {buy|买}=possession OF {obtain|得到}. {buy|买} <----> {obtain|得到} [consequence]; source OF {buy|买}=source OF {obtain|得到}; possession OF {buy|买}=possession OF {obtain|得到}.

Axiomatic Relations & Role Shifting - 2 {buy|买} [entailment] <----> {choose|选择}; agent OF {buy|买}=agent Axiomatic Relations & Role Shifting - 2 {buy|买} [entailment] <----> {choose|选择}; agent OF {buy|买}=agent OF {choose|选择}; possession OF {buy|买}=content OF {choose|选择}; source OF {buy|买}=location OF {choose|选择}. {buy|买} [entailment] <----> {pay|付}; agent OF {buy|买}=agent OF {pay|付}; cost OF {buy|买}=possession OF {pay|付}; source OF {buy|买}=taget OF {pay|付}.

Axiomatic Relations & Role Shifting - 3 {buy|买} (X) <----> {sell|卖} (Y) [mutual implication]; Axiomatic Relations & Role Shifting - 3 {buy|买} (X) <----> {sell|卖} (Y) [mutual implication]; agent OF {buy|买}=target OF {sell|卖}; source OF {buy|买}=agent OF {sell|卖}; possession OF {buy|买}=possession OF {sell|卖}; cost OF {buy|买}=cost OF {sell|卖}.

Identical representation - 1 W_E=smuggle G_E=V DEF={transport|运送: manner={guilty|有罪}} W_E=drug G_E=N DEF={addictive|嗜好物: modifier={guilty|有罪}} Identical representation - 1 W_E=smuggle G_E=V DEF={transport|运送: manner={guilty|有罪}} W_E=drug G_E=N DEF={addictive|嗜好物: modifier={guilty|有罪}}

Identical representation - 2 W_E=smuggling of drugs G_E=N DEF={fact|事情: Co. Event={transport|运送: manner={guilty|有罪}, patient={addictive|嗜好物: modifier={guilty|有罪}}}} Identical representation - 2 W_E=smuggling of drugs G_E=N DEF={fact|事情: Co. Event={transport|运送: manner={guilty|有罪}, patient={addictive|嗜好物: modifier={guilty|有罪}}}} W_E=drug smuggler G_E=N DEF={community|团体: {transport|运送: agent={~}, manner={unlawful|非法}, patient={addictive|嗜好物}, purpose={sell|卖}}}

Types of relations Types of relations

Motivation to develop secondary resources n n n To check from different angles How. Motivation to develop secondary resources n n n To check from different angles How. Net knowledge data for their preciseness and consistency To provide users with tools for application Practible for any sense of any word

Secondary resources Concept Relevance Calculator (CRC) n Concept Similarity Measure (CSM) n Query Expansion Secondary resources Concept Relevance Calculator (CRC) n Concept Similarity Measure (CSM) n Query Expansion Tool (QET) n Chinese Morphological Processor (CMP) n v Chinese Message Analyzer (CMA)

Concept similarity doctor 2 <> dentist doctor 1<> nurse 1 doctor 1<> nurse 2 Concept similarity doctor 2 <> dentist doctor 1<> nurse 1 doctor 1<> nurse 2 doctor 1<> patient walk <> run walk <> jump walk <> swim walk <> fly walk <> buy 0. 300000 0. 883333 0. 620000 0. 454545 0. 203636 0. 144444 0. 130159 0. 124444 0. 018605

Conclusion n n Extralinguistic knowledge is indispensable for HLT The knowledge should be a Conclusion n n Extralinguistic knowledge is indispensable for HLT The knowledge should be a system which is computer-oriented It should be big enough, exemplary toy is useless It can conduct computation of meaning

Thank you Welcome to www. keenage. com! Download and try Mini-How. Net Thank you Welcome to www. keenage. com! Download and try Mini-How. Net