Semantic Role Labeling Abdul-Lateef Yussiff 20-01-2011.

25
Semantic Role Labeling Abdul-Lateef Yussiff 20-01-2011

Transcript of Semantic Role Labeling Abdul-Lateef Yussiff 20-01-2011.

Page 1: Semantic Role Labeling Abdul-Lateef Yussiff 20-01-2011.

Semantic Role Labeling

Abdul-Lateef Yussiff20-01-2011

Page 2: Semantic Role Labeling Abdul-Lateef Yussiff 20-01-2011.

Table of Contents

• Introduction & motivation• Definition Semantic Role• Application Areas• Available corpus• SRL Tasks

Page 3: Semantic Role Labeling Abdul-Lateef Yussiff 20-01-2011.

Introduction & Motivation

• Information extraction and dialogue understanding systems are usually based on domain-specific frame-and-slot templates

• For natural language understanding tasks to proceed beyond domain de-pendent system, semantic under-standing systems is needed.

Page 4: Semantic Role Labeling Abdul-Lateef Yussiff 20-01-2011.

Introduction & Motivation

• Since 1999 CoNLL has organized several shared tasks exploring many NLP problems.

• This research proposal focuses on the problem studied in the CoNLL 2004 and 2005 shared tasks – Namely Semantic Role labeling (SRL).

Page 5: Semantic Role Labeling Abdul-Lateef Yussiff 20-01-2011.

Definition

• A semantic role is the underlying relationships that a participant has with the main verb in a clause. [www.sil.org]

• SRL is detecting basic event structures such as who did what to whom, when and where [IE view]

• SRL is identifying the arguments of a given predicate and assign them semantic labels de-scribing the roles they play in the predicate

[Computational linguistic view]

Page 6: Semantic Role Labeling Abdul-Lateef Yussiff 20-01-2011.

CoNLL Shared tasks

• SRL is the relationship that a syntac-tic constituent has with a predicate.– Core arguments: Agent, Patient, Instru-

ment etc.– Adjunctive arguments: Locative, Tempo-

ral, Manner, Cause, etc.• [http://www.lsi.uoc.edu/~s-rlconll]

Page 7: Semantic Role Labeling Abdul-Lateef Yussiff 20-01-2011.

Example

• Mary hit John• John was hit by Mary

(ROOT (S (NP (NNP John)) (VP (VBD was) (VP (VBN hit) (PP (IN by) (NP (NNP Mary))))) (. .)))

S

VPNP

NNP VBD NNP

Mary hit John

(S (NP (NNP Mary)) (VP (VBD hit) (NP (NNP John))) (. .)))

Page 8: Semantic Role Labeling Abdul-Lateef Yussiff 20-01-2011.

Fundamental tasks in NLP

• Semantic Role labeling is an essential step to-wards the final goal of natural language under-standing.

• Several fundamental tasks in NLP are based on recognizing phrases or constituents.– Noun phrases, Chunking, clause identification,

name entity identification Syntactic analysis, etc.

Page 9: Semantic Role Labeling Abdul-Lateef Yussiff 20-01-2011.

Semantic Role

• A variety of semantic role labels have been proposed, common ones are:– Agent: Actor of an action– Patient: Entity affected by the action– Instrument: Tool used in performing action.– Beneficiary: Entity for whom action is performed– Source: Origin of the affected entity– Destination: Destination of the affected entity

Page 10: Semantic Role Labeling Abdul-Lateef Yussiff 20-01-2011.

Application Areas

• Question Answering– “Who” questions usually use Agents– “What” question usually use Patients– “How” and “with what” questions usually use Instruments– “Where” questions frequently use Sources and Destinations.– “For whom” questions usually use Beneficiaries– “To whom” questions usually use Destinations

• Machine Translation Generation– Semantic roles are usually expressed using particular, dis-

tinct syntactic constructions in different languages.

Page 11: Semantic Role Labeling Abdul-Lateef Yussiff 20-01-2011.

Syntactic cues

• Semantic role is indicated by a particular syn-tactic position (e.g. object of a particular preposition).–Agent: subject–Patient: direct object– Instrument: object of “with” PP–Beneficiary: object of “for” PP–Source: object of “from” PP–Destination: object of “to” PP

Page 12: Semantic Role Labeling Abdul-Lateef Yussiff 20-01-2011.

SRL with Parse Trees• Assume that a syntactic parse is available.• For each predicate (verb), label each node in

the parse tree as either not-a-role or one of the possible semantic roles S

NP VP

NP PP

The

Prep NP

with

the

V NP

bit

a

big

dog girl

boy

Det A NDet A N

εAdj A

ε

Det A N

ε

Page 13: Semantic Role Labeling Abdul-Lateef Yussiff 20-01-2011.

SRL Corpus

• FrameNet: Developed at University of Cali-fornia, Berkeley. Based on notion of frames

• VerbNet• PropBank: Developed at University of Penn-

sylvania. Based on Treebank– Annotated over 1M words of WSJ text– 43, 594 sentences– 3,324 unique roles – 262,281 role assignments

Page 14: Semantic Role Labeling Abdul-Lateef Yussiff 20-01-2011.

<!DOCTYPE frameset SYSTEM "frameset.dtd"><frameset><predicate lemma="abandon">

<roleset framnet="" id="abandon.01" name="leave behind" vncls="51.2"><roles> <role descr="abandoner" f="" n="0">

<vnrole vncls="51.2" vntheta="theme"/></role> <role descr="thing abandoned, left behind" f="" n="1">

<vnrole vncls="51.2" vntheta="source"/></role> <role descr="attribute of arg1" f="" n="2"/><note/></roles>

<example name="typical transitive" src="" type=""><text>And they believe the Big Board, under Mr. Phelan, has abandoned their interest.</text> <arg f="" n="0">the Big Board</arg> <arg f="" n="m">under Mr. Phelan</arg> <rel f="">abandoned</rel> <arg f="" n="1">their interest</arg><note/></example>

<example name="with attribute" src="" type=""> <text>John abandoned his pursuit of an Olympic gold medal as a waste of time.</text> <arg f="" n="0">John</arg> <rel f="">abandoned</rel> <arg f="" n="1">his pursuit of an Olympic gold medal</arg> <arg f="" n="2">as a waste of time.</arg><note/></example>

Example of propBank frameset

Roleset indi-cates different senses of the

verb

Page 15: Semantic Role Labeling Abdul-Lateef Yussiff 20-01-2011.

Example of Corpus

Page 16: Semantic Role Labeling Abdul-Lateef Yussiff 20-01-2011.

SRL TASKS

• I am proposing a two tasks for SRL– Arguments identification:

• Parse the sentence into syntactic constituents• Binary classification of predicates (verb)• Use a binary classification to determine

whether a constituents span a boundary or not

– Argument classification into Semantic roles.• Assign appropriate semantic role to the identi-

fied semantic argument• This is a clearly a multi-class classification

Page 17: Semantic Role Labeling Abdul-Lateef Yussiff 20-01-2011.

System Architecture

Raw Sen-tence

Sentence labeled with

Semantic Roles

Parser

POS & Tree

Argument Iden-tification

Role Classifica-tion

input Output

Page 18: Semantic Role Labeling Abdul-Lateef Yussiff 20-01-2011.

Baseline Features for SRL [Gildea and Jurafsky, 2002 ]

• Phrase type: the syntactic label of the candi-date role (e.g. NP)

• Parse tree path: the path in the parse tree be-tween the predicate and the candidate role

• Position of the phrase type relative to the pred-icate

• voice of the predicate (active or passive)• Head word of the phrase type

Page 19: Semantic Role Labeling Abdul-Lateef Yussiff 20-01-2011.

ChallengesBell, based in Los Angeles, makes and distributes electronic, computer and building products.

[Bell, ,, based, in, Los, Angeles, ,][Bell][Los, Angeles][electronic, ,, computer, and, building, prod-ucts]

Iterator <Tree> iterator = t.iterator(); while (iterator.hasNext()){ Tree node = iterator.next();if(node.value().equalsIgnoreCase("NP")) System.out.println(node.getLeaves()); }//end of while iterator

Page 20: Semantic Role Labeling Abdul-Lateef Yussiff 20-01-2011.

(ROOT (S (NP (NP (NNP Bell)) (, ,) (VP (VBN based) (PP (IN in) (NP (NNP Los) (NNP Angeles)))) (, ,)) (VP (VBZ makes) (CC and) (VBZ distributes) (NP (UCP (JJ electronic) (, ,) (NN computer) (CC and) (NN building)) (NNS products))) (. .)))

Page 21: Semantic Role Labeling Abdul-Lateef Yussiff 20-01-2011.

Baseline Research Work

• Gildea and Jurafsky (2002)– Parse the training corpus using Collin’s

parser–Match frame elements into constituents– Extract features from the parse tree– Train probabilistic model on the model – 82% accuracy for presegmented con-

stituents– 65% precision and 61% recall for segmen-

tation and identification

Page 22: Semantic Role Labeling Abdul-Lateef Yussiff 20-01-2011.

Machine learning ap-proaches

• Maximum entropy• SVM• Enhanced perceptron• Decision Trees• Nearest neighbor• CRF

MESVMNNDTCRFOthers

Page 23: Semantic Role Labeling Abdul-Lateef Yussiff 20-01-2011.

Top Ten Systems in the CoNLL 2005

Page 24: Semantic Role Labeling Abdul-Lateef Yussiff 20-01-2011.

References• Gildea, Daniel and Daniel Jurafsky. 2002. Automatic labeling of semantic

roles. Computational Linguistics 28(3):245–288• Gildea, Daniel and Palmer, Martha. The necessity of parsing for predicate

argument recognition. Proceeding of the 40th Annual Meeting of ACL 2002. pp239.246

• Hao Xiong, Haitao Mi, Yang Liu and Qun Liu. Forest-based Semantic Role Labeling. The Association of Advancement of AI ,2010.

• Klenner Manfred, Extracting predicate structures from parse Trees• Hacioglu Kadri. Semantic role labeling Using dependency Trees• Marquez L, Carreras X., Litkowski K.C., Stevenson Suzanne. Semantic Role

Labeling: An Introduction to special issue. Association for Computational Linguistics 2008.

• Surdeanu M., Marquez L., Carreras X. Comas P. Combination Strategies for Semantic Role Labeling. Journal of AI Research 29:105-151

Page 25: Semantic Role Labeling Abdul-Lateef Yussiff 20-01-2011.

Question ?

THANK YOU FOR YOUR TIME