Download presentation
Presentation is loading. Please wait.
Published byἈγαυή Αθανασιάδης Modified over 6 years ago
1
Syntactic Disambiguation through Lexicon Enrichment
Second Stage Project Presentation Guide: Pushpak Bhattacharyya Ashish Almeida 03M05601
2
Overview Motivation Problem definition Linguistic theory
Lexical enrichment Design and implementation Results Future work December 5, 2018
3
Motivation Robust and scalable UNL generation required
English analysis for extracting meaning Correct analysis correct meaning representation Identification of correct syntactic representation Identification of correct semantic relation December 5, 2018
4
Preposition Phrase Attachment Problem
John covered the baby with a blanket. covered covered John the baby with Wrong ! John the baby a blanket with a blanket Verb attachment Noun attachment December 5, 2018
5
Universal Networking Language
He forwarded the mail to the minister. obj agt @ past minister(icl>person) forward(icl>send) mail(icl>collection) He(icl>person) @def gol December 5, 2018
6
Linguistic Insights Syntactic level Semantic level Syntactic Frame
Subcategorization Semantic level Selectional restrictions Thematic/theta roles December 5, 2018
7
Syntactic Frame Sequence of words as they appear in sentences
[V-ART-N] … handed a book [NP-to-NP] the mail to the minister [V-NP-P-NP] … forwarded the mail to the minister December 5, 2018
8
Subcategorization Verbs He put the book on the table.
put: [ _NP PP-on] Nouns his reliance on/*at/*with her help. *his reliance. reliance: [ _PP-on] Adjectives He is fond of reading. fond: [ _ PP-of] December 5, 2018
9
Selectional Restrictions
The boy murdered John. *The boy murdered the tree. Thus the verb ‘murder’ needs a human as object. murder: [HUMAN _ HUMAN] December 5, 2018
10
Thematic Roles Each argument of verb has a unique role associated with it. Each role is assigned to a single argument. E.g. The boy murdered John. The boy - agent John - patient/theme Other thematic roles : Instrument, locative, goal UNL relations: analogous to thematic roles. December 5, 2018
11
Lexicon Enrichment Idiosyncratic information
Subcategorization Thematic roles in terms of UNL relations How to get this information ? Oxford advanced learner’s dictionary, WordNet UNL relations Beth Levin, manual effort December 5, 2018
12
An Example Dictionary Entry
forward E.g. he forwarded the mail to the minister [forward]{}“forward(icl>sent)” (VRB,VOA,VOA-PHSL, #_TO_A2,#_TO_A2_gol)<E,0,0>; headword Universal Word Attributes December 5, 2018
13
Issues The work focuses on The [V-NP-P-NP] frame
Commonly used prepositions In, on, of, with, from, to, for Disambiguating to Active voice December 5, 2018
14
Design Fill the valency of the nearest element first.
If in the frame [V-N1-P-N2] both V and N1 have #P in their subcategorization frames, then satisfy the demand of the nearest element to P, i.e., the noun first. Else, give priority to that element which subcategorizes the preposition P Else, give priority to the events and actions (can be verb or noun) destroyV, destructionN etc. December 5, 2018
15
Summarization of Algorithm
Conditions Action Attributes of V NP1 NP2 Attachment of Examples 1 #<P> _ N1 …paid a visit to the museum. 2 Not ...passed the ball to Bill. …imposed heavy penalties on fuel dealers. 3 a PLACE …met him in his office. TIME …met him in the afternoon. b #<P>, EVENT …cancelled a meeting with his friends. 5 …supplied plans for projects. December 5, 2018
16
Problems with to Infinitival to Preposition to Problem:
Do not allow onion to brown Preposition to The lights changed from green to brown Problem: Detect if the lexical element is to-preposition or to-infinitive December 5, 2018
17
Heuristics to Detect to-preposition
Criterion Preposition to Infinitival to - to is followed by a determiner - to is followed by a word followed by a plural marker - to is followed by an adjective - to is followed by a proper noun - to is followed by a pronoun - the matrix verb specifies that it needs a to- preposition complement. - to is preceded by a noun which specifies that it needs a to-preposition complement. infinitival complement. needs a to-infinitival complement. - to is followed by a base verb December 5, 2018
18
Implementation Creating new dictionary with extra attributes
Writing new rules to use these new attributes Rules to use subcategorization information Rules for processing events (nouns and verbs) December 5, 2018
19
Analysis Engine (Enconverter)
sentence Word1 Word2 Word3 Word4 … Wordn windows LCW LAW RAW RCW Analysis windows Left Analysis Window (LAW) Right Analysis Window (RAW) Condition windows Many in number LCWs, RCWs December 5, 2018
20
Operations in Analysis
Movement of heads Addition of two nodes Deletion of a node Creating relation between two nodes Adding dynamically inferred attributes to node December 5, 2018
21
Rules R{VRB,#_FOR_AR2:::}{N,#_FOR:::}(PRE,#FOR)P60; IF
; Right shift to affect noun attachment R{VRB,#_FOR_AR2:::}{N,#_FOR:::}(PRE,#FOR)P60; This states that IF The left analysis window is on a verb which takes a for-pp as the second argument (indicated by #_FOR_AR2) AND The right analysis window is on a noun which takes a for-pp as an argument (indicated by #_FOR) The preposition for follows the noun (indicated by (PRE,#FOR) ) THEN Shift right (indicated by R at the start of the rule) anticipating noun attachment for the PP. December 5, 2018
22
Other Rules <{VRB,#_FOR_AR2,#_FOR_AR2_rsn:::}
; Create relation between V and N2, after resolving the preposition preceding N2 <{VRB,#_FOR_AR2,#_FOR_AR2_rsn:::} {N,FORRES,PRERES::rsn:}P25; ;Delete the preposition ON >(VRB,EVENT,VOA){PRE,#ON:::} {N,UNIT,TIME,DAY:+ONRES,+PRERES::}P27; ;Create the relation tim between verb and noun <{VRB,VOA:::} {N,TIME,UNIT,ONRES,PRERES::tim:}P20; December 5, 2018
23
Testing Resources: Filtered out
British National Corpus WordNet Brown corpus Filtered out Phrasal verbs Compound nouns Longer sentences Semantically different types of constructs tested in [V-N-P-N] frame. December 5, 2018
24
Cases of with Different semantic Roles in different syntactic and semantic environments Attachment Semantic relation Example Noun obj He cancelled [a meeting with his students]. and She wore [a green skirt with a blouse]. Verb ins He [covered the baby with a blanket]. gol That [provides him with a living]. ptn He [is playing chess with his friend]. December 5, 2018
25
Results for of-preposition
The results of testing for solving PP attachment and generating UNL Corpus Frames Total no. of Sentences No. of Correct attachments & UNL relations Accuracy % BNC V-N1-of-N2 1000 886 88 WSJ 661 597 90 December 5, 2018
26
Conclusion Lexical enrichment originating from key linguistic principles makes the analysis more correct Rule-base design simplified due to distinction made between complements and adjuncts during analysis December 5, 2018
27
Future Work Handling the alternation patterns of verbs
Applying the algorithm on all prepositions Extracting the information through various resources such as dictionaries and annotated corpus December 5, 2018
28
References UNDL Foundation: The Universal Networking Language (UNL) specifications version 3.2. (2003) Grimshaw, Jane.: Argument Structure. The MIT Press, Cambridge, Mass. (1990) Brill, E. and Resnik, R.: A Rule based approach to Prepositional Phrase Attachment disambiguation. Proc. of the fifteenth International conference on computational linguistics. Kyoto. (1994) Levin, Beth.: English verb Classes and Alternation. The University of Chicago Press, Chicago. (1993) Hornby, A. S.: Oxford Advanced Learner’s Dictionary of Current English. Oxford University Press, Oxford.(2000) December 5, 2018
29
Thank you December 5, 2018
30
Example UNL In I deposited my money in my bank account. {unl} {/unl}
account(icl>statement):0W) money(icl>currency):0F) I:0C) mod(money(icl>currency):0F, I:0C) mod(account(icl> statement):0W, bank(icl>possession):0R) mod(account(icl> statement):0W, I:0O) {/unl} December 5, 2018
31
Example UNL On I put the book on the table. {unl} {/unl}
I:00) {/unl} December 5, 2018
32
Example UNL To They served a wonderful meal to fifty delegates. {unl}
they(icl>thing):00) wonderful(mod<thing):0E) fifty(icl>number):0W) {/unl} December 5, 2018
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.