Automatic Noun Compound Interpretation Stephen Tratz Eduard Hovy University of Southern California/ Information Sciences Institute.

Slides:



Advertisements
Similar presentations
Specialized models and ranking for coreference resolution Pascal Denis ALPAGE Project Team INRIA Rocquencourt F Le Chesnay, France Jason Baldridge.
Advertisements

The Impact of Task and Corpus on Event Extraction Systems Ralph Grishman New York University Malta, May 2010 NYU.
Automatic Identification of Cognates, False Friends, and Partial Cognates University of Ottawa, Canada University of Ottawa, Canada.
MT Evaluation: Human Measures and Assessment Methods : Machine Translation Alon Lavie February 23, 2011.
1 A Comparative Evaluation of Deep and Shallow Approaches to the Automatic Detection of Common Grammatical Errors Joachim Wagner, Jennifer Foster, and.
Scott Wen-tau Yih (Microsoft Research) Joint work with Vahed Qazvinian (University of Michigan)
The University of Wisconsin-Madison Universal Morphological Analysis using Structured Nearest Neighbor Prediction Young-Bum Kim, João V. Graça, and Benjamin.
Automatic Discovery of Technology Trends from Patent Text Youngho Kim, Yingshi Tian, Yoonjae Jeong, Ryu Jihee, Sung-Hyon Myaeng School of Engineering Information.
Predicting the Semantic Orientation of Adjective Vasileios Hatzivassiloglou and Kathleen R. McKeown Presented By Yash Satsangi.
1 CSC 594 Topics in AI – Applied Natural Language Processing Fall 2009/ Shallow Parsing.
1 Noun Homograph Disambiguation Using Local Context in Large Text Corpora Marti A. Hearst Presented by: Heng Ji Mar. 29, 2004.
Boosting Applied to Tagging and PP Attachment By Aviad Barzilai.
Designing clustering methods for ontology building: The Mo’K workbench Authors: Gilles Bisson, Claire Nédellec and Dolores Cañamero Presenter: Ovidiu Fortu.
Dept. of Computer Science & Engg. Indian Institute of Technology Kharagpur Part-of-Speech Tagging and Chunking with Maximum Entropy Model Sandipan Dandapat.
Text Mining: Finding Nuggets in Mountains of Textual Data Jochen Dörre, Peter Gerstl, and Roland Seiffert Presented By: Jake Happs,
Extracting Opinions, Opinion Holders, and Topics Expressed in Online News Media Text Soo-Min Kim and Eduard Hovy USC Information Sciences Institute 4676.
ERC StG: Multilingual Joint Word Sense Disambiguation (MultiJEDI) Roberto Navigli 1 A Graph-based Algorithm for Inducing Lexical Taxonomies from Scratch.
Richard Socher Cliff Chiung-Yu Lin Andrew Y. Ng Christopher D. Manning
COMP423: Intelligent Agent Text Representation. Menu – Bag of words – Phrase – Semantics – Bag of concepts – Semantic distance between two words.
Automatic Extraction of Opinion Propositions and their Holders Steven Bethard, Hong Yu, Ashley Thornton, Vasileios Hatzivassiloglou and Dan Jurafsky Department.
Processing of large document collections Part 3 (Evaluation of text classifiers, applications of text categorization) Helena Ahonen-Myka Spring 2005.
Empirical Methods in Information Extraction Claire Cardie Appeared in AI Magazine, 18:4, Summarized by Seong-Bae Park.
Carmen Banea, Rada Mihalcea University of North Texas A Bootstrapping Method for Building Subjectivity Lexicons for Languages.
1 A study on automatically extracted keywords in text categorization Authors:Anette Hulth and Be´ata B. Megyesi From:ACL 2006 Reporter: 陳永祥 Date:2007/10/16.
A Compositional Context Sensitive Multi-document Summarizer: Exploring the Factors That Influence Summarization Ani Nenkova, Stanford University Lucy Vanderwende,
Assessing the Impact of Frame Semantics on Textual Entailment Authors: Aljoscha Burchardt, Marco Pennacchiotti, Stefan Thater, Manfred Pinkal Saarland.
2007. Software Engineering Laboratory, School of Computer Science S E Towards Answering Opinion Questions: Separating Facts from Opinions and Identifying.
Iterative Readability Computation for Domain-Specific Resources By Jin Zhao and Min-Yen Kan 11/06/2010.
Document Categorization Problem: given –a collection of documents, and –a taxonomy of subject areas Classification: Determine the subject area(s) most.
PAUL ALEXANDRU CHIRITA STEFANIA COSTACHE SIEGFRIED HANDSCHUH WOLFGANG NEJDL 1* L3S RESEARCH CENTER 2* NATIONAL UNIVERSITY OF IRELAND PROCEEDINGS OF THE.
Exploring a Hybrid of Support Vector Machines (SVMs) and a Heuristic Based System in Classifying Web Pages Santa Clara, California, USA Ahmad Rahman, Yuliya.
1 The Ferret Copy Detector Finding short passages of similar texts in large document collections Relevance to natural computing: System is based on processing.
Incident Threading for News Passages (CIKM 09) Speaker: Yi-lin,Hsu Advisor: Dr. Koh, Jia-ling. Date:2010/06/14.
Annotating Words using WordNet Semantic Glosses Julian Szymański Department of Computer Systems Architecture, Faculty of Electronics, Telecommunications.
Paper Review by Utsav Sinha August, 2015 Part of assignment in CS 671: Natural Language Processing, IIT Kanpur.
Crowdsourcing for Spoken Dialogue System Evaluation Ling 575 Spoken Dialog April 30, 2015.
Efficiently Computed Lexical Chains As an Intermediate Representation for Automatic Text Summarization H.G. Silber and K.F. McCoy University of Delaware.
A Bootstrapping Method for Building Subjectivity Lexicons for Languages with Scarce Resources Author: Carmen Banea, Rada Mihalcea, Janyce Wiebe Source:
Opinion Holders in Opinion Text from Online Newspapers Youngho Kim, Yuchul Jung and Sung-Hyon Myaeng Reporter: Chia-Ying Lee Advisor: Prof. Hsin-Hsi Chen.
Ideas for 100K Word Data Set for Human and Machine Learning Lori Levin Alon Lavie Jaime Carbonell Language Technologies Institute Carnegie Mellon University.
Wikipedia as Sense Inventory to Improve Diversity in Web Search Results Celina SantamariaJulio GonzaloJavier Artiles nlp.uned.es UNED,c/Juan del Rosal,
Detecting a Continuum of Compositionality in Phrasal Verbs Diana McCarthy & Bill Keller & John Carroll University of Sussex This research was supported.
SemEval-2010 Task 8 Multi-Way Classification of Semantic Relations Between Pairs of Nominals 1. Task Description Iris Hendrickx, Su Nam Kim, Zornitsa Kozareva,
Prototype-Driven Learning for Sequence Models Aria Haghighi and Dan Klein University of California Berkeley Slides prepared by Andrew Carlson for the Semi-
Minimally Supervised Event Causality Identification Quang Do, Yee Seng, and Dan Roth University of Illinois at Urbana-Champaign 1 EMNLP-2011.
Automatic Identification of Pro and Con Reasons in Online Reviews Soo-Min Kim and Eduard Hovy USC Information Sciences Institute Proceedings of the COLING/ACL.
Supertagging CMSC Natural Language Processing January 31, 2006.
1 Generating Comparative Summaries of Contradictory Opinions in Text (CIKM09’)Hyun Duk Kim, ChengXiang Zhai 2010/05/24 Yu-wen,Hsu.
UWMS Data Mining Workshop Content Analysis: Automated Summarizing Prof. Marti Hearst SIMS 202, Lecture 16.
Improved Video Categorization from Text Metadata and User Comments ACM SIGIR 2011:Research and development in Information Retrieval - Katja Filippova -
Acquisition of Categorized Named Entities for Web Search Marius Pasca Google Inc. from Conference on Information and Knowledge Management (CIKM) ’04.
Using Wikipedia for Hierarchical Finer Categorization of Named Entities Aasish Pappu Language Technologies Institute Carnegie Mellon University PACLIC.
Exploiting Named Entity Taggers in a Second Language Thamar Solorio Computer Science Department National Institute of Astrophysics, Optics and Electronics.
From Words to Senses: A Case Study of Subjectivity Recognition Author: Fangzhong Su & Katja Markert (University of Leeds, UK) Source: COLING 2008 Reporter:
Event-Based Extractive Summarization E. Filatova and V. Hatzivassiloglou Department of Computer Science Columbia University (ACL 2004)
11 A Classification-based Approach to Question Routing in Community Question Answering Tom Chao Zhou 1, Michael R. Lyu 1, Irwin King 1,2 1 The Chinese.
Virtual Examples for Text Classification with Support Vector Machines Manabu Sassano Proceedings of the 2003 Conference on Emprical Methods in Natural.
Cheap and Fast – But is it Good? Evaluating Non-Expert Annotations for Natural Language Tasks EMNLP 2008 Rion Snow CS Stanford Brendan O’Connor Dolores.
Towards Semi-Automated Annotation for Prepositional Phrase Attachment Sara Rosenthal William J. Lipovsky Kathleen McKeown Kapil Thadani Jacob Andreas Columbia.
Learning Event Durations from Event Descriptions Feng Pan, Rutu Mulkar, Jerry R. Hobbs University of Southern California ACL ’ 06.
Overview of Statistical NLP IR Group Meeting March 7, 2006.
Multi-Class Sentiment Analysis with Clustering and Score Representation Yan Zhu.
Language Identification and Part-of-Speech Tagging
Noun Compounds Interpretation简单调研
Review-Level Aspect-Based Sentiment Analysis Using an Ontology
Automatic Detection of Causal Relations for Question Answering
Text Mining & Natural Language Processing
Using Uneven Margins SVM and Perceptron for IE
CS224N Section 3: Corpora, etc.
Extracting Why Text Segment from Web Based on Grammar-gram
Presentation transcript:

Automatic Noun Compound Interpretation Stephen Tratz Eduard Hovy University of Southern California/ Information Sciences Institute

Noun Compound Definition A head noun with one or more preceding noun modifiers Examples: uranium rod, mountain cave, terrorist attack Other names – noun-noun compound – noun sequence – compound nominal – complex nominal

Problem 1: Relation between modifier and head nouns – uranium rod (n 1 substance-of n 2 ) – mountain cave (n 1 location-of n 2 ) – terrorist attack (n 1 performer-of n 2 ) Problem 2: Structure of long noun compounds – ((aluminum soup) (pot cover)) – ((aluminum (soup pot)) cover) – (aluminum ((soup pot) cover)) The Problems

The Need Needed for natural language understanding – Question answering – Recognition of textual entailment – Summarization – Summarization evaluation – Etc

Solution A taxonomy of relations that occur between nouns in noun compounds Wide coverage of relations Good definitions High inter-annotator agreement An automatic classification method For supervised approaches, this requires a sufficiently large annotated dataset

Weaknesses of earlier solutions Limited-quality/usefulness relations Using unlimited number of relations Using a few ambiguous relations such as prepositions and a handful of simple verbs (e.g., BE, HAVE, CAUSE) --- still need to disambiguate! Definitions are sometimes not provided Low inter-annotator agreement Limited annotated data (problem for supervised classification)

Dataset Dataset of 17.5k noun compounds from: – a large dataset extracted using mutual information plus part-of-speech tagging – the WSJ portion of the Penn Treebank

Dataset Comparison SizeWork 17509Tratz and Hovy, Kim and Baldwin, *Girju, Rosario and Hearst, Ó Séaghdha and Copestake, *Barker and Szpakowicz, *Nastase and Szpakowicz, Vanderwende, Lauer, 1995

Our Semantic Relations Relation taxonomy 43 relations Relatively fine-grained Defined using sentences Have rough mappings to relations used in well- known noun compound research papers

Relation examples Substance/Material/Ingredient Of (uranium rod) – n 1 is one of the primary physical substances/ materials/ingredients that n 2 is made out of/from Location Of (mountain cave) – n 1 is the location / geographic scope where n 2 is at, near, from, generally found, or occurs.

All The Relations Communica tor of Communica tion Performer of Act/Activity Creator/Pro vider/Cause Of Perform/En gage_In Create/Prov ide/Sell Obtain/Acce ss/Seek Modify/Proc ess/Change Mitigate/Op pose/Destro y Organize/S upervise/Au thority Propel Protect/Con serve Transport/T ransfer/Trad e Traverse/Vi sit Possessor + Owned/Pos sessed Experiencer + Cognition/M ental Employer+ Employee/V olunteer Consumer + Consumed User/Recipi ent + Used/Recei ved Owned/Pos sessed + Possession Experiencer + Experiencer Thing Consumed + Consumer Thing/Mean s Used + User Time [Span] + X X + Time [Span] Location/Geographic Scope of X Whole + Part/Member Of Substance/Material/In gredient + Whole Part/Member + Collection/Configurati on/Series X + Spatial Container/Location/B ounds Topic of Communication/Imag ery/Info Topic of Plan/Deal/Arrangeme nt/Rules Topic of Observation/Study/Ev aluation Topic of Cognition/Emotion Topic of Expert Topic of Situation Topic of Event/Process Topic/Thing + Attribute Topic/Thing + Attribute Value Characteristic Of Coreferential Partial Attribute Transfer Measure + Whole Highly Lexicalized / Fixed Pair Other

Taxonomy Creation Taxonomy created by Inspecting a large number of examples Comparing relations to those in literature Refining relations using Mechanical Turk Upload data for annotation Analyze annotations Make changes Repeat (5x)

Inter-annotator agreement study What: – Calculate the level of agreement between two or more sets of annotations Why: – Human agreement typically represents an upper bound on machine performance How: – Used Amazon's Mechanical Turk service to collect a set of annotations

Reasons for using Turk Inexpensive – Paid $0.08 per decision Low startup time – Don't have to wait long for people to start working Relatively fast turnaround

Problems with using Turk Mixed annotator quality No training for the annotators No guarantee of native English speakers Different number of annotations per Turker – Can't force someone to annotate everything – Problem for 3+ annotator agreement formula (Fleiss' Kappa)

Solution: Combine Turkers Requested 10 annotations per compound Calculated a weight for each Turker based upon his/her level of agreement with other Turkers – Average percentage of annotations that agreed with the Turker Used weights to created a single set of annotations Ignored Turkers who performed less than 3 annotations

Agreement Scores Calculated raw agreement – # agreements / # decisions Cohen's Kappa – Adjusts for chance agreement

Id Agree % κκ*κ** Combined Auto Agreement Results

Individual Turker Agreement (vs author, N >= 15)

Turker vote weight vs Agreement Correlation for Turkers who performed 15 or more vs Agreement: 0.92

Comparison to other studies

Automatic Classification Method Maximum Entropy classifier – SVM multiclass gave similar performance after optimizing the C parameter Large number of boolean features extracted for each word from WordNet Roget's Thesaurus Web 1T Corpus the spelling of the words

Features Used Synonyms Hypernyms Definition words Lexicographer Ids Link types (e.g., part-of) List of different types of part-of-speech entries All parts-of Prefixes, suffixes Roget's division information Last letters of the word Trigrams and 4-grams from Web 1T corpus Some combinations of features (e.g. shared hypernyms) A handful of others

Cross-validation experiments Performed one-feature-type-only and all-but- one experiments for the different types of features Most useful features – Hypernyms – Definition words – Synonyms – Web 1T trigrams and 4-grams

Conclusion Novel taxonomy 43 fine-grained relations Defined using sentences with placeholders for the nouns Achieved relatively high inter- annotator agreement given the difficulty of the task Largest annotated dataset Over 8 times larger than the next largest Automatic classification method Achieves performance approximately.10 less than human inter-annotator agreement

Future Work Address structural issues of longer (3+ word) compounds Merge relation set with The Preposition Project (Litkowski, 2002) relations for prepositions Integrate into a dependency parser

The End Thank you for listening Questions?