Manually querying search engines in order to accumulate a large bodyof factual information is a tedious, error-prone process of piecemealsearch. Search engines retrieve and rank potentially relevantdocuments for human perusal, but do not extract facts, assessconfidence, or fuse information from multiple documents. This paperintroduces KnowItAll, a system that aims to automate the tedious process ofextracting large collections of facts from the web in an autonomous,domain-independent, and scalable manner.The paper describes preliminary experiments in which an instance of KnowItAll, running for four days on a single machine, was able to automatically extract 54,753 facts. KnowItAll associates a probability with each fact enabling it to trade off precision and recall. The paper analyzes KnowItAll's architecture and reports on lessons learned for the design of large-scale information extraction systems.

/pdf/web-scale-information-extraction-in-knowitall-preliminary-258uazal0e.pdf

Web-scale information extraction in knowitall: (preliminary results)

Broad-coverage repositories of semantic relations between verbs could benefit many NLP tasks. We present a semi-automatic method for extracting fine-grained semantic relations between verbs. We detect similarity, strength, antonymy, enablement, and temporal happens-before relations between pairs of strongly associated verbs using lexicosyntactic patterns over the Web. On a set of 29,165 strongly associated verb pairs, our extraction algorithm yielded 65.5% accuracy. Analysis of error types shows that on the relation strength we achieved 75% accuracy. We provide the resource, called VERBOCEAN, for download at http://semantics.isi.edu/ocean/.

/pdf/verbocean-mining-the-web-for-fine-grained-semantic-verb-5edrpovdin.pdf

VerbOcean: Mining the Web for Fine-Grained Semantic Verb Relations

/pdf/overview-of-the-trec-2002-question-answering-track-nist-2r0er182wu.pdf

Overview of the TREC 2002 Question Answering Track | NIST

In the last few years, a number of NLP researchers have developed and participated in the task of Recognizing Textual Entailment (RTE). This task encapsulates Natural Language Understanding capabilities within a very simple interface: recognizing when the meaning of a text snippet is contained in the meaning of a second piece of text. This simple abstraction of an exceedingly complex problem has broad appeal partly because it can be conceived also as a component in other NLP applications, from Machine Translation to Semantic Search to Information Extraction. It also avoids commitment to any specific meaning representation and reasoning framework, broadening its appeal within the research community. This level of abstraction also facilitates evaluation, a crucial component of any technological advancement program. This book explains the RTE task formulation adopted by the NLP research community, and gives a clear overview of research in this area. It draws out commonalities in this research, detailing the intuitions behind dominant approaches and their theoretical underpinnings. This book has been written with a wide audience in mind, but is intended to inform all readers about the state of the art in this fascinating field, to give a clear understanding of the principles underlying RTE research to date, and to highlight the short- and long-term research goals that will advance this technology.

Recognizing Textual Entailment: Models and Applications

Word sense disambiguation (WSD), the task of identifying the intended meanings (senses) of words in context, has been a long-standing research objective for natural language processing. In this paper, we are concerned with graph-based algorithms for large-scale WSD. Under this framework, finding the right sense for a given word amounts to identifying the most ?important? node among the set of graph nodes representing its senses. We introduce a graph-based WSD algorithm which has few parameters and does not require sense-annotated data for training. Using this algorithm, we investigate several measures of graph connectivity with the aim of identifying those best suited for WSD. We also examine how the chosen lexicon and its connectivity influences WSD performance. We report results on standard data sets and show that our graph-based approach performs comparably to the state of the art.

/pdf/an-experimental-study-of-graph-connectivity-for-unsupervised-25dsxky8kw.pdf

An Experimental Study of Graph Connectivity for Unsupervised Word Sense Disambiguation

¢¡¤£`¥T¦ §© ̈/¥ a"«­¬g® ̄©°M±2¬ ́3/μ¬ ́¶°M·] ̧!1^o»¬M1⁄4­®»1⁄2a3⁄4j·/¿W1⁄22«­¬ a"À|ÁÃÂ ÄÅÇÆ0È­¬ ́μ21⁄22®»·] ̄©μ"±~¬ ́Æ0È©®É±2¬ ́μn3/¶©Ê 3/ ̄©°M¬ ́¶ 1⁄2¬M1⁄4L1⁄2c1^±2· Ë °M¬ ́μ~μ2®É ̄­ÌD1⁄2· ·]oÉμn1⁄22«©3 1⁄2|±~¬ ́o»3⁄4Í·] ̄ ̄©3 1⁄22È­±H3/oRoÉ3/ ̄­Ì]È^3 Ì/¬A1©±2·L°M¬ ́μ2μ2® ̄­ÌD3/ ̄©¶jÎL ̄­·dÏ|o»¬ ́¶­Ì/¬g±2¬ ́3/μ·] ̄©®É ̄©Ì­ÐÃa|«©®Éμ 153 1@¬`± 1©±2¬ ́μ¬ ́ ̄01⁄22μJ1⁄22«­¬nμ~È©®»1⁄2¬|·/¿R1⁄2·0·]oÉμ 1⁄22«©3 1⁄2Ã3/°`°M·]È© ̄01⁄2J¿,·/±J1⁄22«­¬n1-¬`±2¿,·/±~ ̧D3/ ̄^°M¬|·/¿61⁄22«­¬Ñ¤·TÏJ¬`±~Ån ̄^μÏ ¬`± Æ È­¬ ́μ1⁄22®É·] ̄ 3/ ̄©μ2Ï ¬`±~® ̄­Ì{μ23⁄4 μ1⁄2¬ ́ ̧jÐÓÒa1⁄2®Éμμ2«­·dÏ| ̄V«­·TÏ Æ È­¬ ́μ1⁄22®»·] ̄©μ ́Ô-3/ ̄^μÏ ¬`±Hμc3/ ̄^¶ ÏJ·/±~oÉ¶ ÎL ̄­·TÏ|oÉ¬ ́¶­Ì/¬ 3 ±~¬ 1⁄2±~3/ ̄©μ2¿E·/±~ ̧D¬ ́¶ÖÕ©±~μ21⁄2×®É ̄ØoÉ·/Ì]®É°Ù±2¬`1©±~¬ ́μ¬ ́ ̄1⁄223 1⁄22®É·] ̄6Ô"¿,·]oÉo»·TÏJ¬ ́¶ÖÚ 3⁄4Ö3\μ23⁄4 μ1⁄2¬ ́ ̧×3 1⁄22®É° 3/ ̄^¶Ö±~®»Ì/·/±~·]È©μ oÉ·/Ì]®É°Í1©±2· ·/¿|1⁄22«©3 1⁄2×Ê 3/oÉ®¶©o»3⁄4\3/ ̄©μ2Ï ¬`±~μ×Æ0È­¬ ́μ21⁄22®»·] ̄©μ 1-·]μ¬ ́¶ 1⁄2·Û1⁄22«©¬ ÄÅÜμ23⁄4 μ1⁄2¬ ́ ̧jÐØÅÃ1⁄2×a"ÀnÁJÂÝÄÅ Þ ß/ß]Þ Ô©Ñ¤·dÏ ¬`±~Åc ̄©μÏJ¬`± ·/Ú©1⁄223/®É ̄©¬ ́¶¢3 °M·] ̄­Õ^¶©¬ ́ ̄©°M¬MËGÏ ¬ ́®ÉÌ]«1⁄2¬ ́¶Íμ2°M·/±2¬·/¿RßLÐáà/â/ã Ô53/ ̄©μÏJ¬`±~®É ̄­Ì8°M·/±2±2¬ ́°M1⁄22o»3⁄4 ä©å â!·]È­1⁄2"·/¿Wâ ß/ßDÆ È­¬ ́μ1⁄22®»·] ̄©μ ́Ð

/pdf/lcc-tools-for-question-answering-2gpqmb30yy.pdf

LCC Tools for Question Answering.

The paper presents a method for finding topically related words on an extended WordNet. By exploiting the information in the WordNet glosses, the connectivity between the synsets is dramatically increased. Topical relations expressed as lexical chains on extended WordNet improve the performance of a question answering system by increasing the document retrieval recall and by providing the much needed axioms that link question keywords with answers.

/pdf/lexical-chains-for-question-answering-3qrpv0b39v.pdf

Lexical chains for question answering

http://www.hlt.utdallas.edu/~moldovan/newpapers/j04dman.pdf

Word sense disambiguation of WordNet glosses

This paper describes an algorithm for propagating verb arguments along lexical chains consisting of WordNet relations. The algorithm creates verb argument structures using VerbNet syntactic patterns. In order to increase the coverage, a larger set of verb senses were automatically associated with the existing patterns from VerbNet. The algorithm is used in an in-house Question Answering system for re-ranking the set of candidate answers. Tests on factoid questions from TREC 2004 indicate that the algorithm improved the system performance by 2.4%.

http://www.hlt.utdallas.edu/~moldovan/newpapers/c06andm.pdf

Question Answering with Lexical Chains Propagating Verb Arguments

This document describes the Word Sense Disambiguation system used by Language Computer Corporation at English Coarse Grained All Word Task at SemEval 2007. The system is based on two supervised machine learning algorithms: Maximum Entropy and Support Vector Machines. These algorithms were trained on a corpus created from Sem-Cor, Senseval 2 and 3 all words and lexical sample corpora and Open Mind Word Expert 1.0 corpus. We used topical, syntactic and semantic features. Some semantic features were created using WordNet glosses with semantic relations tagged manually and automatically as part of eXtended WordNet project. We also tried to create more training instances from the disambiguated WordNet glosses found in XWN project (XWN, 2003). For words for which we could not build a sense classifier, we used First Sense in WordNet as a back-off strategy in order to have coverage of 100%. The precision and recall of the overall system is 81.446% placing it in the top 5 systems.

/pdf/lcc-wsd-system-description-for-english-coarse-grained-all-vsfrbhz86k.pdf

Adrian Novischi

Papers

LCC Tools for Question Answering.

Lexical chains for question answering

Word sense disambiguation of WordNet glosses

Question Answering with Lexical Chains Propagating Verb Arguments

LCC-WSD: System Description for English Coarse Grained All Words Task at SemEval 2007