Creation of English and Hindi Verb Hierarchies and their Application to Hindi WordNet Building and English-Hindi MT Debasri Chakrabarti, Gajanan Krishna.

Slides:



Advertisements
Similar presentations
CS460/IT632 Natural Language Processing/Language Technology for the Web Lecture 2 (06/01/06) Prof. Pushpak Bhattacharyya IIT Bombay Part of Speech (PoS)
Advertisements

Syntax-Semantics Mapping Rajat Kumar Mohanty CFILT.
Knowledge Representation
The Universal Networking Language UNL Foundation United Nations University Institute of Advanced Studies United Networking Language ® UNU/IAS.
Statistical NLP: Lecture 3
1 Syntactic Alternations of Hindi Verbs with Reference to the Morphological Paradigm Debasri Chakrabarti Debasri Chakrabarti Dr. Pushpak Bhattacharyya.
Example Database English-German Dictionary
CSE Department, I.I.T. Bombay Automatic Lexicon Generation through WordNet by Nitin Verma and Pushpak Bhattacharyya Jan 21, 2004.
1 Generative Lexicon- Idea and Practicality Debasri Chakrabarti Guide: Prof.Milind S. Malshe Co-Guide: Prof. Pushpak Bhattacharyya.
1 Introduction to Computational Linguistics Eleni Miltsakaki AUTH Fall 2005-Lecture 2.
Universal Networking Language
1 CSC 594 Topics in AI – Applied Natural Language Processing Fall 2009/ Outline of English Syntax.
1 Indo WordNet A WordNet for Hindi Centre for Technology Development for Indian Languages Computer Science and Engineering Department, IIT Bombay.
Notes for CS3310 Artificial Intelligence Part 2: Representation of facts Prof. Neil C. Rowe Naval Postgraduate School Version of January 2006.
Universal Networking Language (UNL) by Pantha Kanti Nath (05IT6021) Under the Guidance of Prof. Debasis Samanta School of Information Technology Indian.
Artificial Intelligence for Universal Networking Language (UNL) (Perspective Bengali Language) By Deen Islam Muslim ID: Ariful Hoque Tuhin ID:
Frames and semantic networks, page 1 CSI 4106, Winter 2005 A brief look at semantic networks A semantic network is an irregular graph that has concepts.
Syntax Lecture 8: Verb Types 1. Introduction We have seen: – The subject starts off close to the verb, but moves to specifier of IP – The verb starts.
GUIDE : Prof. Amitabha Mukerjee By :Amit Kumar (10074) Ankit Modi (10104)
8 November 2003 PP attachment problem1 Prepositional Phrase Attachment Problem 03M05601 Ashish Almeida.
IV. SYNTAX. 1.1 What is syntax? Syntax is the study of how sentences are structured, or in other words, it tries to state what words can be combined with.
CS460/626 : Natural Language Processing/Speech, NLP and the Web (Lecture 37– Semantics; Universal Networking Language) Pushpak Bhattacharyya CSE Dept.,
Jennie Ning Zheng Linda Melchor Ferhat Omur. Contents Introduction WordNet Application – WordNet Data Structure - WordNet FrameNet Application – FrameNet.
Development of NE Wordnet: An Integrated Wordnet for Languages of the North-East India Assamese & Bodo by Utpal Saikia Biswajit Brahma Dibyajyoti Sarmah.
Integrating Semantic Dictionaries for English, French and Bulgarian into the NooJ System for the Purposes of Information Retrieval Svetla Koeva, Max Silbetztein.
© Ch. Boitet & Wang-Ju Tsai (GETA, CLIPS) ICUKL-2002, Goa, 25-29/11/02 1 Proposals for solving some problems in UNL encoding International Conference on.
CS : NLP, Speech and Web-Topics-in-AI Pushpak Bhattacharyya CSE Dept., IIT Bombay Lecture 35: Semantic Relations; UNL; Towards Dependency Parsing.
CS460/IT632 Natural Language Processing/Language Technology for the Web Guest Lecture (31/03/06) Prof. Niladri Chatterjee IIT Delhi Guest Lecture on Machine.
Semantic web course – Computer Engineering Department – Sharif Univ. of Technology – Fall Knowledge Representation Semantic Web - Fall 2005 Computer.
Linguistic Essentials
Vishal Vachhani CFILT and DIL, IIT Bombay CS 671 ICT For Development 19 th Sep 2008.
Detection of Links between Words in the Task of Syntactic-Semantic Analysis of Russian Texts. Dmitry V. Merkuryev Saint-Petersburg State University, Russia.
Or, what to call every word in the English language.
Rules, Movement, Ambiguity
Generic Tasks by Ihab M. Amer Graduate Student Computer Science Dept. AUC, Cairo, Egypt.
Description of Information Resources: RDF/RDFS (an Introduction)
Some Thoughts to Consider 8 How difficult is it to get a group of people, or a group of companies, or a group of nations to agree on a particular ontology?
1 Introduction to Computational Linguistics Eleni Miltsakaki AUTH Spring 2006-Lecture 2.
Commonsense Reasoning in and over Natural Language Hugo Liu, Push Singh Media Laboratory of MIT The 8 th International Conference on Knowledge- Based Intelligent.
11/23/00UNU/IAS/UNL Centre1 The Universal Networking Language United Nations University Institute of Advanced Studies United Networking Language ® UNU/IAS.
Knowledge Structure Vijay Meena ( ) Gaurav Meena ( )
VOCABULARY BUILDING ONE. WORDS ARE A GROUP OF LETTERS WHICH FORM A MEANING.
An Introduction to Semantic Parts of Speech Rajat Kumar Mohanty rkm[AT]cse[DOT]iitb[DOT]ac[DOT]in Centre for Indian Language Technology Department of Computer.
Semantic Grounding of Tag Relatedness in Social Bookmarking Systems Ciro Cattuto, Dominik Benz, Andreas Hotho, Gerd Stumme ISWC 2008 Hyewon Lim January.
Semantic Interoperability in GIS N. L. Sarda Suman Somavarapu.
7.2 Programming Languages - An Introduction to Informatics WMN Lab. Hye-Jin Lee.
TRUE or FALSE? Syntax= the order of words in a sentence.
Descriptive Grammar – 2S, 2016 Mrs. Belén Berríos
EXTRACTING COMPLEX PREDICATES IN HINDI ACROSS PARALLEL CORPORA
UNIFIED MEDICAL LANGUAGE SYSTEMS (UMLS)
Standardization of Lexicon
Syntax Lecture 9: Verb Types 1.
Statistical NLP: Lecture 3
A Parser for Sinhala Language First Step Towards English to Sinhala Machine Translation
The Great Fire of London
CSC 594 Topics in AI – Applied Natural Language Processing
Creation of English and Hindi Verb Hierarchies and their Application to Hindi WordNet Building and English-Hindi MT Debasri Chakrabarti, Gajanan Krishna.
Syntactic Disambiguation through Lexicon Enrichment
Parts of Speech Mr. White English I.
Preposition Phrase Attachment in English Language Analysis
Introduction to FrameNet and Verb Knowledge Base
X-bar Schema Linguistics lecture series
Towards Semantics Generation
Linguistic Essentials
The Complexity of OF in English
Interpreting Tables and Graphs
Giannis Varelas Epimenidis Voutsakis Paraskevi Raftopoulou
Automatic generation of UW Dictionary through WordNet
Structure of a Lexicon Debasri Chakrabarti 13-May-19.
Deniz Beser A Fundamental Tradeoff in Knowledge Representation and Reasoning Hector J. Levesque and Ronald J. Brachman.
Presentation transcript:

Creation of English and Hindi Verb Hierarchies and their Application to Hindi WordNet Building and English-Hindi MT Debasri Chakrabarti, Gajanan Krishna Rane, Pushpak Bhattacharyya. Computer Science and Engineering Department, Indian Institute of Technology, Bombay, Mumbai, 40076, India. debasri,gkrane,pb@cse.iitb.ac.in 2/2/2019 C.F.I.L.T., I.I.T. BOMBAY

Introduction Verb hierarchy System is based on creation of the verb hierarchy for English and Hindi verbs. organized according to semantics and syntax semantic hierarchy - through the super-ordinate terms and the inbuilt ontology of the UNL KB. syntactic information- through UNL case relations System is based on English verb classes and their alternation (Levin) UNL System: UW Manual, Knowledge base (KB) & specification Semantic relations of English WordNet 2/2/2019 C.F.I.L.T., I.I.T. BOMBAY

Levin’s Class of English verbs Classification of the English verbs Adopted from English Verb Classes and Alternation of Beth Levin. Details of Levin’s work Levin’s classification of the English verb is the most significant and celebrated work. Assumption underlying Levin’s work Syntactic behavior of a verb is semantically determined Levin investigated and exploited this hypothesis for about 3200 English verbs. 2/2/2019 C.F.I.L.T., I.I.T. BOMBAY

Details of Levin’s work Verb Classes Preliminary Investigation considerable correlation between some facets of the semantics of verbs and their syntactic behavior 200 semantic classes defined in Levin’s system each class share a number of alternations Example of verb classes verbs of putting , verbs of communication, correspond verbs etc. 2/2/2019 C.F.I.L.T., I.I.T. BOMBAY

The Universal Networking Language (UNL) electronic language for computers to express and exchange information. UNL system consists Universal words (UW) : Vocabulary of UNL Relations, attributes : Syntax of UNL UNL knowledge base (KB): Semantics of UNL 2/2/2019 C.F.I.L.T., I.I.T. BOMBAY

The Universal Networking Language UNL represents information sentence-by-sentence as a hyper-graph concepts as nodes and relations as arcs Sentence is a hyper-graph a node in the structure can itself be a graph the node is called a compound word (CW) 2/2/2019 C.F.I.L.T., I.I.T. BOMBAY

Graphical representation in UNL @ entry @ present eat (icl>do) agt obj ins John (iof>person) rice (icl>food) spoon (icl>artifact) John eats rice with a spoon 2/2/2019 C.F.I.L.T., I.I.T. BOMBAY

Verbal Concepts in UNL Verbal concepts in the UNL system are organized into three categories (icl>do) for defining the concept of an event which is caused by something or someone change (icl>do) : as in She changed the dress (icl>occur) for defining the concept of an event that happens of its own accord change (icl>occur) : as in The weather will change (icl>be) for defining the concept of a state verb remember (icl>be) : as in Do you remember me? 2/2/2019 C.F.I.L.T., I.I.T. BOMBAY

Verbal Concepts in UNL Partial hierarchical structure for do do(agt>thing{,^gol>thing,icl>do,^obj>thing,^ptn>thing,^src>thing}) do(agt>volitional thing{,icl>do(agt>thing)}) do(agt>living thing{,icl>do(agt>volitional thing)}) do(agt>human{>living thing,icl>do(agt>living thing)}) do(agt>thing,gol>thing{,icl>do, ^obj>thing,^ptn>thing,^src>thing}) Partial hierarchical structure for do 2/2/2019 C.F.I.L.T., I.I.T. BOMBAY

do in UNL KB Semantic hierarchy in terms of the inbuilt ontology in KB do(agt>thing,gol>thing{,icl>do},obj>thing{,^ptn>thing,^src>thing}) do({icl>do(}agt>thing{,gol>thing,obj>thing)},gol>abstract thing,obj>abstract thing) do({icl>do(}agt>thing{,gol>abstract thing,obj>abstract thing)},gol>custom{>abstract thing},ob j>custom{>abstract thing}) do(gol>thing) do(gol>abstract thing) do(gol>custom) 2/2/2019 C.F.I.L.T., I.I.T. BOMBAY

Creation of the verb hierarchy First, a particular verb class is selected from Levin. Next the class is categorized according to the UNL format Parent node of a class is obtained through English wordnet and various dictionaries 2/2/2019 C.F.I.L.T., I.I.T. BOMBAY

Creation of the verb hierarchy “put” ‘Put your clothes in the cupboard’. (to put something into a certain place) (icl>move(agt>person,obj>concrete thing,gol>place) (loc_prep{in/on/into/under/over}) [VTRANS, VOA-ACT] “hang” ‘He hanged the wallpaper on the wall’. (to suspend or fasten something so that it is held up from above and not supported from below) (icl>put{>move}(agt>person,obj>concrete thing,gol>place) (loc_prep{from/on}) Partial hierarchy of the put class 2/2/2019 C.F.I.L.T., I.I.T. BOMBAY

Verb Hierarchy in Hindi रखना ; rakhanaa; r«kHna ‘put’ ‘Put your things here.’ (to put something into a certain place) (icl>act(agt>person,obj>concrete thing,gol>place) अपना सामान यहाँ पर रखो।; («pna saman y«ha) p«r r«kHo) ; apanaa saamaana yahaa par rakho) {(adv_plc (यहाँ/वहाँ / ‘y«ha) / v«ha)’ loc_postp (पर ‘p«r’)} रखना, सजाना ; r«kHna, s«jana; rakhanaa , sajaanaa; ‘arrange’ ‘he arranged the books here’.(to put into a proper or systematic manner) (icl>put{>act}(agt>person,obj>thing) उसने किताबों को यहाँ पर सजाकर रखा। usne kitabo) ko y«ha) p«r s«jak«r r«kHa.) (usne kitabo ko yahaa par sajaakar rakhaa.) {(adv_man (सजाकर, s«jak«r ;क्रम से, kr«m se))+ (adv_plc (यहाँ/वहाँ / ‘y«ha) / v«ha)’ ))+ loc_postp( पर ‘p«r’)} 2/2/2019 C.F.I.L.T., I.I.T. BOMBAY

Verb Hierarchy in Hindi Syntax frames specified for the put class in English (adv_plc{here/there}) (loc_prep) Sentence frames for put in Hindi adv_man adv_plc + adv_man loc_postp + adv_man English Hindi adv_plc (here / there) adv_man (सजाकर, s«jak«r; क्रम से, kr«m se etc ) loc_prep (in, inside, on etc) adv_plc(यहाँ/वहाँ / ‘y«ha) / v«ha)’) +loc_postp(पर ‘p«r)+adv_man (सजाकर, s«jak«r ;क्रम से, kr«m se etc) loc_postp(के उपर, ke up«r etc)+adv_man (सजाकर, s«jak«r etc) 2/2/2019 C.F.I.L.T., I.I.T. BOMBAY

Verb hierarchy and the Hindi WordNet Application of the hierarchy in the Hindi wordnet will help in determining semantic relations like hypernymy and troponymy syntactic frames revealed facts like difference in the representations for troponyms in Hindi and English reclassifications of the verbs in Hindi 2/2/2019 C.F.I.L.T., I.I.T. BOMBAY

Representations of Troponyms English sentence Hindi put put your things here. रखना r«kHna अपना सामान यहाँ पर रखो।; («pna s«man y«ha) p«r r«kHo) pile pile your books up on the shelves. ----- उसने खाने में एक के ऊपर एक सामान रखा।;((((((usne kHane me) ek ke Up«r ek saman r«kHa) cram she cram the books into the suitcase. उसने बक्से के अन्दर सारी किताब ठूँसकर रखी।;(usne bakse ke a)d«r sari kitab tHu)sak«r r«kHI)) 2/2/2019 C.F.I.L.T., I.I.T. BOMBAY

Classification of Hindi Verbs simple compound noun + verb Verbs adjective + verb adverb + verb conjunct 2/2/2019 C.F.I.L.T., I.I.T. BOMBAY

Classification of the Hindi Verbs Simple verbs खाना(kHana) ‘to eat’ Compound verbs गिर पड़ना(gir p«êna) ‘to fall down’ Conjunct verbs noun + verb आरंभ करना (ar«mbH k«rna) ‘to start’ adjective +verb शांत करना (Sant k«rna) ‘to calm down’ adverb + verb उठाकर रखना (utak«r r«kHna) ‘to lift’ 2/2/2019 C.F.I.L.T., I.I.T. BOMBAY

Reclassification of the Hindi verbs Sentence frames of the verbs reveals only noun+ verb conjunct is a true conjunct Hence, a re-classification of the verbs is needed 2/2/2019 C.F.I.L.T., I.I.T. BOMBAY

Application in NLP The application of the verb hierarchy in NLP gives semantic hierarchy of a verbal concept enumerates syntactic details of a verb UNL based MT will be immensely benefited possible UNL relations that appear with a concept is specified 2/2/2019 C.F.I.L.T., I.I.T. BOMBAY

Application in MT Verb Sentence Frame UNL Relations fight Sam and Sue fought. conj_and agt>person Sam was fighting with Sue. prep_accompaniment{with} agt>person, ptn>person The tribesmen fought each other. -prep_with agt>person, obj>person 2/2/2019 C.F.I.L.T., I.I.T. BOMBAY

Conclusion System statistics approximately 3000 English verbs approximately 5500 UWs Common English verbs are dealt with tested against British National Corpus Coverage of both English and Hindi verbs is increasing everyday Visualizer and an application programming interface for the verb knowledge bases in both the languages are under construction 2/2/2019 C.F.I.L.T., I.I.T. BOMBAY