Semantic Role Labeling for Arabic using Kernel Methods Mona Diab Alessandro Moschitti Daniele Pighin.

Slides:



Advertisements
Similar presentations
School of something FACULTY OF OTHER School of Computing FACULTY OF ENGINEERING Chunking: Shallow Parsing Eric Atwell, Language Research Group.
Advertisements

CS460/IT632 Natural Language Processing/Language Technology for the Web Lecture 2 (06/01/06) Prof. Pushpak Bhattacharyya IIT Bombay Part of Speech (PoS)
SEMANTIC ROLE LABELING BY TAGGING SYNTACTIC CHUNKS
Lexical Functional Grammar History: –Joan Bresnan (linguist, MIT and Stanford) –Ron Kaplan (computational psycholinguist, Xerox PARC) –Around 1978.
Progress update Lin Ziheng. System overview 2 Components – Connective classifier Features from Pitler and Nenkova (2009): – Connective: because – Self.
The NOUN 1 General characteristics and classification
Syntactic analysis using Context Free Grammars. Analysis of language Morphological analysis – Chairs, Part Of Speech (POS) tagging – The/DT man/NN left/VBD.
Sequence Classification: Chunking Shallow Processing Techniques for NLP Ling570 November 28, 2011.
Grammatical Relations and Lexical Functional Grammar Grammar Formalisms Spring Term 2004.
计算机科学与技术学院 Chinese Semantic Role Labeling with Dependency-driven Constituent Parse Tree Structure Hongling Wang, Bukang Wang Guodong Zhou NLP Lab, School.
Statistical NLP: Lecture 3
Semantic Role Labeling Abdul-Lateef Yussiff
A Joint Model For Semantic Role Labeling Aria Haghighi, Kristina Toutanova, Christopher D. Manning Computer Science Department Stanford University.
Steven Schoonover.  What is VerbNet?  Levin Classification  In-depth look at VerbNet  Evolution of VerbNet  What is FrameNet?  Applications.
 Christel Kemke 2007/08 COMP 4060 Natural Language Processing Feature Structures and Unification.
NLP and Speech 2004 Feature Structures Feature Structures and Unification.
Stemming, tagging and chunking Text analysis short of parsing.
SRL using complete syntactic analysis Mihai Surdeanu and Jordi Turmo TALP Research Center Universitat Politècnica de Catalunya.
DS-to-PS conversion Fei Xia University of Washington July 29,
Two-Phase Semantic Role Labeling based on Support Vector Machines Kyung-Mi Park Young-Sook Hwang Hae-Chang Rim NLP Lab. Korea Univ.
1 CSC 594 Topics in AI – Applied Natural Language Processing Fall 2009/ Shallow Parsing.
Elicitation Corpus April 12, Agenda Tagging with feature vectors or feature structures Combinatorics Extensions.
1 I256: Applied Natural Language Processing Marti Hearst Sept 25, 2006.
SI485i : NLP Set 9 Advanced PCFGs Some slides from Chris Manning.
11 CS 388: Natural Language Processing: Syntactic Parsing Raymond J. Mooney University of Texas at Austin.
Context Free Grammars Reading: Chap 12-13, Jurafsky & Martin This slide set was adapted from J. Martin, U. Colorado Instructor: Paul Tarau, based on Rada.
9/8/20151 Natural Language Processing Lecture Notes 1.
Empirical Methods in Information Extraction Claire Cardie Appeared in AI Magazine, 18:4, Summarized by Seong-Bae Park.
Tree Kernels for Parsing: (Collins & Duffy, 2001) Advanced Statistical Methods in NLP Ling 572 February 28, 2012.
1 CPE 480 Natural Language Processing Lecture 5: Parser Asst. Prof. Nuttanart Facundes, Ph.D.
Assessing the Impact of Frame Semantics on Textual Entailment Authors: Aljoscha Burchardt, Marco Pennacchiotti, Stefan Thater, Manfred Pinkal Saarland.
Interpreting Dictionary Definitions Dan Tecuci May 2002.
Ling 570 Day 17: Named Entity Recognition Chunking.
AQUAINT Workshop – June 2003 Improved Semantic Role Parsing Kadri Hacioglu, Sameer Pradhan, Valerie Krugler, Steven Bethard, Ashley Thornton, Wayne Ward,
INSTITUTE OF COMPUTING TECHNOLOGY Forest-based Semantic Role Labeling Hao Xiong, Haitao Mi, Yang Liu and Qun Liu Institute of Computing Technology Academy.
A Cascaded Finite-State Parser for German Michael Schiehlen Institut für Maschinelle Sprachverarbeitung Universität Stuttgart
A Cross-Lingual ILP Solution to Zero Anaphora Resolution Ryu Iida & Massimo Poesio (ACL-HLT 2011)
A Systematic Exploration of the Feature Space for Relation Extraction Jing Jiang & ChengXiang Zhai Department of Computer Science University of Illinois,
Linguistic Essentials
Semantic Construction lecture 2. Semantic Construction Is there a systematic way of constructing semantic representation from a sentence of English? This.
CPE 480 Natural Language Processing Lecture 4: Syntax Adapted from Owen Rambow’s slides for CSc Fall 2006.
Rules, Movement, Ambiguity
An Ambiguity-Controlled Morphological Analyzer for Modern Standard Arabic By: Mohammed A. Attia Abbas Al-Julaih Natural Language Processing ICS.
Multilingual Opinion Holder Identification Using Author and Authority Viewpoints Yohei Seki, Noriko Kando,Masaki Aono Toyohashi University of Technology.
Automatically detecting and describing high level actions within methods Presented by: Gayani Samaraweera.
Supertagging CMSC Natural Language Processing January 31, 2006.
CPSC 422, Lecture 27Slide 1 Intelligent Systems (AI-2) Computer Science cpsc422, Lecture 27 Nov, 16, 2015.
Support Vector Machines and Kernel Methods for Co-Reference Resolution 2007 Summer Workshop on Human Language Technology Center for Language and Speech.
11 Project, Part 3. Outline Basics of supervised learning using Naïve Bayes (using a simpler example) Features for the project 2.
Chunk Parsing. Also called chunking, light parsing, or partial parsing. Method: Assign some additional structure to input over tagging Used when full.
Overview of Statistical NLP IR Group Meeting March 7, 2006.
Web Intelligence and Intelligent Agent Technology 2008.
Learning to Generate Complex Morphology for Machine Translation Einat Minkov †, Kristina Toutanova* and Hisami Suzuki* *Microsoft Research † Carnegie Mellon.
COSC 6336: Natural Language Processing
Lecture – VIII Monojit Choudhury RS, CSE, IIT Kharagpur
Lecture 3: Functional Phrases
Syntax Lecture 9: Verb Types 1.
Statistical NLP: Lecture 3
INAGO Project Automatic Knowledge Base Generation from Text for Interactive Question Answering.
Representation of Actions as an Interlingua
Syntax.
CS 388: Natural Language Processing: Syntactic Parsing
LING/C SC 581: Advanced Computational Linguistics
Automatic Detection of Causal Relations for Question Answering
CSCI 5832 Natural Language Processing
Linguistic Essentials
Progress report on Semantic Role Labeling
Extracting Why Text Segment from Web Based on Grammar-gram
Owen Rambow 6 Minutes.
Presentation transcript:

Semantic Role Labeling for Arabic using Kernel Methods Mona Diab Alessandro Moschitti Daniele Pighin

What is SRL? Proposition John opened the door

What is SRL? Proposition [John] Agent [opened] Predicate [the door] Theme

What is SRL? Proposition [John] Agent [opened] Predicate [the door] Theme Subject Object

What is SRL? Proposition [John] Agent [opened] Predicate [the door] Theme Subject Object [The door] Theme [opened] Predicate

What is SRL? Proposition [John] Agent [opened] Predicate [the door] Theme Object Subject [The door] Theme [opened] Predicate

What is SRL? Proposition [John] Agent [opened] Predicate [the door] Theme FrameNet Agent Container_portal [The door] Theme [opened] Predicate

What is SRL? Proposition [John] Agent [opened] Predicate [the door] Theme PropBank ARG0 ARG1 [The door] Theme [opened] Predicate

Why SRL? Useful for information extraction Useful for Question Answering Useful for Machine Translation?

Our Goal Last Sunday India to official visit Rongji Zhu the- Chinese the-Ministers president started The Chinese Prime Minister Zho Rongji started an official visit to India last sunday

Our Goal Last Sunday India to official visit Rongji Zhu the- Chinese the-Ministers president started The Chinese Prime Minister Zho Rongji started an official visit to India last Sunday ARGM-TMP

RoadMap Arabic Characteristics Our Approach Experiments & Results Conclusions & Future Directions

Morphology Rich complex morphology –Templatic, concatenative, derivational, inflectional wbHsnAthm w+b+Hsn+At+hm and by virtue(s) their –Verbs are marked for tense, person, gender, aspect, mood, voice –Nominals are marked for case, number, gender, definiteness Orthography is underspecified for short vowels and consonant doubling (diacritics)

Syntax Pro-drop language –Akl AlbrtqAl‘[he] ate the orange(s)’ –hw Akl AlbrtqAl‘he ate the orange(s)’ Relative free word order –VSO, SVO, OVS, etc. –The canonical order is VSO, dialects are more SVO –In Arabic Treebank v3.2 we observe equal distribution of SVO (35%) and VSO (35%) and pro-drop (30%) Complex noun phrases expressing possession ‘idafa constructions –mlk AlArdn‘king_INDEF Jordan’ king of Jordan

Characteristics relevant for SRL Typical underspecification of short vowels masks morphological features such as case and agreement –Example: rjl Albyt Alkbyr Man_ masc the-house_ masc the-big_ masc “the big man of the house” or “the man of the big house”

Characteristics relevant for SRL Typical underspecification of short vowels masks morphological features such as case and agreement –Example: rjlu Albyti Alkbyri Man_ masc-Nom the-house_ masc-Gen the-big_ masc-Gen the man of the big house

Characteristics relevant for SRL Typical underspecification of short vowels masks morphological features such as case and agreement –Example: rjlu Albyti Alkbyru Man_ masc-Nom the-house_ masc-Gen the-big_ masc-Nom the big man of the house

Characteristics relevant for SRL Idafa constructions make indefinite nominals syntactically definite hence allowing for agreement, therefore better scoping –Example: [rjlu Albyti] Alkbyru Man_ masc-Nom-Def the-house_ masc-Gen the-big_ masc-Nom- Def the big man of the house

Characteristics relevant for SRL Passive constructions are hard to detect due to underspecified short vowels marking passivization inflection. Best automatic systems are at 68% acc. –Example: qtl Emr bslAH qAtl…. [He] pro-drop killed Amr by a deadly weapon… Amr killed by a deadly weapon … Amr was killed by a deadly weapon ….

Characteristics relevant for SRL Passive constructions are hard to detect due to underspecified short vowels marking passivization inflection. Hence –Example: qatal Emra _ACC_ARG1 bslAHiK qAtliK…. [He] pro-drop killed Amr _ACC_ARG1 by a deadly weapon… Amr killed by a deadly weapon … Amr was killed by a deadly weapon ….

Characteristics relevant for SRL Passive constructions are hard to detect due to underspecified short vowels marking passivization inflection. Hence –Example: qatal Emru_ NOM_ARG0 bslAHiK qAtliK…. [He] pro-drop killed Amr by a deadly weapon… Amr _NOM_ARG0 killed by a deadly weapon … Amr was killed by a deadly weapon ….

Characteristics relevant for SRL Passive constructions are hard to detect due to underspecified short vowels marking passivization inflection. Hence –Example: qutil Emru _NOM_ARG1 bslAHiK qAtliK…. [He] pro-drop killed Amr by a deadly weapon… Amr killed by a deadly weapon … Amr _NOM_ARG1 was killed by a deadly weapon ….

Characteristics relevant for SRL Passive constructions differ from English in that they can not have an explicit non- instrument underlying subject, hence only ARG1 and ARG2. ARG0 are not allowed. –Example: qutil Emru bslAHiK qAtliK *qutl [Emru] ARG1 [bslmY] ARG0 *[Amr] ARG1 was killed [by SalmA] ARG0

Characteristics relevant for SRL Passive constructions differ from English in that they can not have an explicit non- instrument underlying subject, hence only ARG1 and ARG2. ARG0 are not allowed. –Example: qutil [Emru] ARG1 [bslAHiK qAtliK] ARG2 [Amr] ARG1 was killed [by a deadly weapon] ARG2

Characteristics relevant for SRL Relative free word order combined by agreement patterns between Subject and Verb could be helpful when explicit yet confusing with absence of case and passive marker and pro-drop VSO = Gender agreement only between V and S SVO = Gender and Number agreement

Our Approach

Semantic Role Labeling Steps Given a sentence and an associated syntactic parse An SRL system identifies the arguments for a given predicate The arguments are identified in two steps –Argument boundary detection –Argument role classification For the overall system we apply a heuristic for argument label conflict resolution one label per argument

The Sentence The Chinese Prime Minister Zho Rongji started an official visit to India last sunday

The Parse Tree

Boundary Identification

Role Classification

Our Approach Experiment with different kernels Experiment with Standard Features (similar to English) and rich morphological features specific to Arabic

Different Kernels Polynomial Kernels (1-6) with standard features Tree Kernels Where N t 1 and N t 2 are the sets of nodes in t 1 and t 2, and Δ(.) evaluates the common substructures rooted in n 1 and n 2

Argument Structure Trees (AST) NP D N VP V delivers a talk S N Paul in PP IN NP jj formal N style Arg. 1 Defined as the minimal subtree encompassing the predicate and one of its arguments

Tree Substructure Representations NP D N VP V delivers a talk NP D N VP V delivers a NP D N VP V delivers NP D N VP V NP VP V

The overall set of AST substructures

Explicit feature space counts the number of common substructures

Standard Features Predicate: Lemmatization of the predicate Path: Syntactic path linking the predicate and an argument NN  NP  VP  VBD Partial Path: Path feature limited to the branching of arg No Direction path without the traversals Phrase type Last and first POS of words in the arguments Verb subcategorization frame: production expanding the predicate parent node Position of the argument relative to predicate Syntactic Frame: positions of the surrounding NPs relative to predicate

Extended Features for Arabic Definiteness, Number, Gender, Case, Mood, Person, Lemma (vocalized), English Gloss, Unvocalized surface form, Vocalized Surface form Expanded the leaf nodes in AST with 10 attribute value pairs creating EAST

Arabic AST Sample AST from our example ARG0

Arabic AST Sample AST from our example ARG0

Extended AST (EAST) ……

Experiments & Results

Experimental Set Up SemEval 2007 Task 18 data set, Pilot Arabic Propbank 95 most frequent verbs in ATB3v2 Gold parses, Unvowelized, Bies reduced POS tag set (25 tags) Num Sentences: Dev (886), Test (902), Train (8402) 26 role types (5 numbered ARGs)

Experimental Set Up Experimented only with 350k examples We use the SVM-Light TK Toolkit (Moschitti, 2004, 2006) with SVM light default parameters Evaluation metrics of precision, recall and F measure are obtained using the CoNLL evaluator

Boundary Detection Results

Role Classification Results

Overall Results

Observations-BD AST and EAST don’t differ much for boundary detection AST+EAST+ Poly (3) gives best BD results AST and EAST perform significantly better than Poly (1)

Observations – RC & SRL For classification, EAST is 2 absolute f-score points better than AST AST is better than Poly(1) and EAST is better than Poly(1) and AST for both classification and overall system Poly 2 and 3 are similar to EAST in classification AST+EAST+best Poly, Poly(3), yields best classification results Best results yielded are for ARG0 and ARG1 ARG1 because of passive cases in Arabic is harder than in English

Conclusions Explicitly encoding the rich morphological features helps with SRL in Arabic Tree Kernels is indeed a feasible way of dealing with large feature spaces that are structural in nature Combining kernels yields better results

Future Directions Experiment with richer POS tag sets Experiment with automatic parses Experiment with different syntactic formalisms Integrate polynomial kernels with tree kernels Experiment with better conflict resolution approaches

Thank You

The parse tree