1. CS460/626 : Natural Language Processing/Speech, NLP and the Web (Lecture 37– Semantics; Universal Networking Language) Pushpak Bhattacharyya CSE Dept., IIT Bombay 12 th April, 2011

2. Semantics: wikipedia Semantics (from Greek sēmantiká, neuter plural of sēmantikós) is the study of meaning.Greekmeaning It typically focuses on the relation between signifiers, such as words, phrases, signs and symbols, and what they stand for, their denotata.words phrasessignssymbolsdenotata

3. Computational Semantics: wikipedia Computational semantics is the study of how to automate the process of constructing and reasoning with meaning representations of natural language expressions.meaning representations natural language Some traditional topics of interest are: construction of meaning representations, semantic underspecification, anaphora resolution, presupposition projection, and quantifier scope resolution.construction of meaning representationsunderspecificationanaphora presuppositionquantifier Methods employed usually draw from formal semantics or statistical semantics.formal semanticsstatistical semantics Computational semantics has points of contact with the areas of lexical semantics (word sense disambiguation and semantic role labeling), discourse semantics, knowledge representation and automated reasoning (in particular, automated theorem proving). lexical semanticsword sense disambiguationsemantic role labelingknowledge representation automated reasoningautomated theorem proving Since 1999 there has been an ACL special interest group on computational semantics, SIGSEM.ACL

4. A hurdle: signifier-denotata dichotomy Divide between a word and what it stands for “red” is NOT red in colour “red wine”, “red rose”, “he is in the red” denote very different sense of the word Translation into another language reveals this difference

5. A Perpective Morphology Lexicon Syntax Semantics Pragmatics Discourse

6. Our tryst with semantics: Universal Networking Language (UNL)

7. Motivation Extraction of semantics, i.e., deep meaning is important for many applications. Machine Translation, Meaning-based IR, CLIR Robust, scalable & efficient methods of knowledge extraction required Machine Translation and Cross Lingual IR: a need of the hour for crossing language barrier 7

8. Interlingua: a vehicle for machine translation Interlingua (UNL) English French Hindi Chinese generation Analysis 8

9. UNL: a United Nations project Started in 1996 10 year program 15 research groups across continents First goal: generators Next goal: analysers (needs solving various ambiguity problems) Current active language groups UNL_French (GETA-CLIPS, IMAG) UNL_English+Hindi UNL_Italian (Univ. of Pisa) UNL_Portugese (Univ of Sao Paolo, Brazil) UNL_Russian (Institute of Linguistics, Moscow) UNL_Spanish (UPM, Madrid) 9

10. 10 World-wide Universal Networking Language (UNL) Project UNL English Russian Japanese Hindi Spanish Language independent meaning representation. Marathi Others

11. 11 The UNL MT System: an Overview

12. NLP@IITB 12

13. Foundations and Applications UNL Foundations Semantic Relations Universal Words Attributes How to write UNL expressions UNL Applications Machine Translation: Rule based and Statistical Search Text Entailment Sentiment Analysis 13

14. Language Processing & Understanding Information Extraction: Part of Speech tagging Named Entity Recognition Shallow Parsing Summarization Machine Learning: Semantic Role labeling Sentiment Analysis Text Entailment (web 2.0 applications) Using graphical models, support vector machines, neural networks IR: Cross Lingual Search Crawling Indexing Multilingual Relevance Feedback Machine Translation: Statistical Interlingua Based English  Indian languages Indian languages  Indian languages Indowordnet Resources: http://www.cfilt.iitb.ac.inhttp://www.cfilt.iitb.ac.in Publications: http://www.cse.iitb.ac.in/~pbhttp://www.cse.iitb.ac.in/~pb Linguistics is the eye and computation the body

15. UNL represents knowledge: John eats rice with a spoon Semantic relations attributes Universal words Repository of 42 Semantic Relations and 84 attribute labels 15

16. Sentence embeddings Deepa claimed that she had composed a poem. [UNL] agt(claim.@entry.@past, Deepa) obj(claim.@entry.@past, :01) agt:01(compose.@past.@entry.@complete, she) obj:01(compose.@past.@entry.@complete, poem.@indef) [\UNL] 16

17. 17 Constituents of Universal Networking Language Universal Words (UWs) Relations Attributes Knowledge Base

18. 18 UNL Graph obj agt @ entry @ past minister(icl>person) forward(icl>send) mail(icl>collection) he(icl>person) @def gol He forwarded the mail to the minister.

19. 19 UNL Expression agt (forward(icl>send).@ entry @ past, he(icl>person)) obj (forward(icl>send).@ entry @ past, minister(icl>person)) gol (forward(icl>send ).@ entry @ past, mail(icl>collection). @def)

20. 20 What is a Universal Word (UW)? Words of UNL Constitute the UNL vocabulary, the syntactic- semantic units to form UNL expressions A UW represents a concept Basic UW (an English word/compound word/phrase with no restrictions or Constraint List) Restricted UW (with a Constraint List ) Examples: “crane(icl>device)” “crane(icl>bird)”

21. 21 The Lexicon Format of the dictionary entry e.g., [minister] {} “minister(icl>person)” (N,ANIMT,PHSCL,PRSN); Head word Universal word Attributes Morphological- Pl(plural), V_ed(past tense form) Syntactic - V(verb),VOA(verb of action) Semantic - ANIMT(animate), PLACE, TIME [headword] {} “Universal word“ (Attribute list);

22. 22 The Lexicon (cntd) Content words: [forward] {} “forward(icl>send)” (V,VOA) ; [mail] {} “mail(icl>message)” (N,PHSCL,INANI) ; [minister] {} “minister(icl>person)” (N,ANIMT,PHSCL,PRSN) ; HeadwordUniversal WordAttributes He forwarded the mail to the minister.

23. 23 The Lexicon (cntd) function words: [he] {} “he” (PRON,SUB,SING,3RD) ; [the] {} “the” (ART,THE) ; [to] {} “to” (PRE,#TO) ; HeadwordUniversal Word Attributes He forwarded the mail to the minister.

24. Hindi example: संज्ञा का उदाहरण १ / २ सार्वभौम शब्द मुख्य शब्द farmer(icl>creator)farmer शेतकरी किसान N,M,ANIMT,FAUNA,MML,PRSN,Na N,ANIMT,FAUNA,MML,PRSN E M H N,M,ANIMT,FAUNA,MML,PRSN गुण

25. 25 The Features of a UW Every concept existing in any language must correspond to a UW The constraint list should be as small as necessary to disambiguate the headword Every UW should be defined in the UNL Knowledge-Base

26. 26 Restricted UWs Examples He will hold office until the spring of next year. The spring was broken. Restricted UWs, which are Headwords with a constraint list, for example: “spring(icl>season)” “spring(icl>device)” “spring(icl>jump)” “spring(icl>fountain)”

27. 27 How to create UWs? Pick up a concept the concept of “crane" as "a device for lifting heavy loads” or as “a long-legged bird that wade in water in search of food” Choose an English word for the concept. In the case for “crane", since it is a word of English, the corresponding word should be ‘crane' Choose a constraint list for the word. [ ] ‘crane(icl>device)' [ ] ‘crane(icl>bird)'

28. How to create UNL expressions

29. English sentences: basic structure A B John eats bread agt(eat.@entry, John) obj(eat.@entry, bread) A John sleeps aoj(sleep.@entry, John) A B John is good aoj(good.@entry, John) verb A R1R1 R2R2 B A aoj verb BA R1R1 R2R2

30. Hindi sentences: basic structure A B John roti khaataa hai agt(eat.@entry, John) obj(eat.@entry, bread) A John sotaa hai aoj(sleep.@entry, John) A B John acchaa hai aoj(good.@entry, John) verb A R1R1 R2R2 B A aoj verb BA R1R1 R2R2

31. :02 :01 Complex English sentences: Use recursion on the basic structure A B John who is a good boy eats bread which is toasted agt(eat.@entry, :01) obj(eat.@entry, :02) aoj:01(boy, John.@entry) mod:01(boy, good) obj:01(toast, bread.@entry.@focus) boy John aoj toast Bread obj eat :02:01 agtobj good mod Red arrows indicate entry nodes