It’s a Contradiction – no, it’s not: A Case Study using Functional Relations

Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pages 11–20, Honolulu, October 2008. c⃝2008 Association for Computational Linguistics It’s a Contradiction—No, it’s Not: A Case Study using Functional Relations Alan Ritter, Doug Downey, Stephen Soderland and Oren Etzioni Turing Center Department of Computer Science and Engineering University of Washington Box 352350 Seattle, WA 98195, USA {aritter,ddowney,soderlan,etzioni}@cs.washington.edu Abstract Contradiction Detection (CD) in text is a difficult NLP task. We investigate CD over functions (e.g., BornIn(Person)=Place), and present a domain-independent algorithm that automatically discovers phrases denoting functions with high precision. Previous work on CD has investigated hand-chosen sentence pairs. In contrast, we automatically harvested from the Web pairs of sentences that appear contradictory, but were surprised to find that most pairs are in fact consistent. For example, “Mozart was born in Salzburg” does not con- tradict “Mozart was born in Austria” despite the functional nature of the phrase “was born in”. We show that background knowledge about meronyms (e.g., Salzburg is in Austria), synonyms, functions, and more is essential for success in the CD task. 1 Introduction and Motivation Detecting contradictory statements is an important and challenging NLP task with a wide range of potential applications including analysis of politi- cal discourse, of scientific literature, and more (de Marneffe et al., 2008; Condoravdi et al., 2003; Harabagiu et al., 2006). De Marneffe et al. present a model of CD that defines the task, analyzes different types of contradictions, and reports on a CD system. They report 23% precision and 19% recall at detect- ing contradictions in the RTE-3 data set (Voorhees, 2008). Although RTE-3 contains a wide variety of contradictions, it does not reflect the prevalence of seeming contradictions and the paucity of genuine contradictions, which we have found in our corpus. 1.1 Contradictions and World Knowledge Our paper is motivated in part by de Marneffe et al.’s work, but with some important differences. First, we introduce a simple logical foundation for the CD task, which suggests that extensive world knowl- edge is essential for building a domain-independent CD system. Second, we automatically generate a large corpus of apparent contradictions found in ar- bitrary Web text. We show that most of these appar- ent contradictions are actually consistent statements due to meronyms (Alan Turing was born in London and in England), synonyms (George Bush is mar- ried to both Mrs. Bush and Laura Bush), hypernyms (Mozart died of both renal failure and kidney dis- ease), and reference ambiguity (one John Smith was born in 1997 and a different John Smith in 1883). Next, we show how background knowledge enables a CD system to discard seeming contradictions and focus on genuine ones. De Marneffe et al. introduced a typology of con- tradiction in text, but focused primarily on contra- dictions that can be detected from linguistic evi- dence (e.g. negation, antonymy, and structural or lexical disagreements). We extend their analysis to a class of contradictions that can only be detected utilizing background knowledge. Consider for ex- ample the following …

Content truncated to 500 words