Contextual Preferences

Proceedings of ACL-08: HLT, pages 683–691, Columbus, Ohio, USA, June 2008. c⃝2008 Association for Computational Linguistics Contextual Preferences Idan Szpektor, Ido Dagan, Roy Bar-Haim Department of Computer Science Bar-Ilan University Ramat Gan, Israel {szpekti,dagan,barhair}@cs.biu.ac.il Jacob Goldberger School of Engineering Bar-Ilan University Ramat Gan, Israel goldbej@eng.biu.ac.il Abstract The validity of semantic inferences depends on the contexts in which they are applied. We propose a generic framework for handling contextual considerations within applied in- ference, termed Contextual Preferences. This framework defines the various context-aware components needed for inference and their relationships. Contextual preferences extend and generalize previous notions, such as se- lectional preferences, while experiments show that the extended framework allows improving inference quality on real application data. 1 Introduction Applied semantic inference is typically concerned with inferring a target meaning from a given text. For example, to answer “Who wrote Idomeneo?”, Question Answering (QA) systems need to infer the target meaning ‘Mozart wrote Idomeneo’ from a given text “Mozart composed Idomeneo”. Following common Textual Entailment terminology (Giampic- colo et al., 2007), we denote the target meaning by h (for hypothesis) and the given text by t. A typical applied inference operation is matching. Sometimes, h can be directly matched in t (in the example above, if the given sentence would be liter- ally “Mozart wrote Idomeneo”). Generally, the tar- get meaning can be expressed in t in many differ- ent ways. Indirect matching is then needed, using inference knowledge that may be captured through rules, termed here entailment rules. In our exam- ple, ‘Mozart wrote Idomeneo’ can be inferred using the rule ‘X compose Y → X write Y ’. Recently, several algorithms were proposed for automatically learning entailment rules and paraphrases (viewed as bi-directional entailment rules) (Lin and Pantel, 2001; Ravichandran and Hovy, 2002; Shinyama et al., 2002; Szpektor et al., 2004; Sekine, 2005). A common practice is to try matching the struc- ture of h, or of the left-hand-side of a rule r, within t. However, context should be considered to allow valid matching. For example, suppose that to find acquisitions of companies we specify the target tem- plate hypothesis (a hypothesis with variables) ‘X ac- quire Y ’. This h should not be matched in “children acquire language quickly”, because in this context Y is not a company. Similarly, the rule ‘X charge Y → X accuse Y ’ should not be applied to “This store charged my account”, since the assumed sense of ‘charge’ in the rule is different than its sense in the text. Thus, the intended contexts for h and r and the context within the given t should be prop- erly matched to verify valid inference. Context matching at inference time was of- ten approached in an application-specific manner (Harabagiu et al., 2003; Patwardhan and Riloff, 2007). Recently, some generic methods were pro- posed to handle context-sensitive inference (Dagan et al., 2006; Pantel et al., 2007; Downey et al., 2007; Connor and Roth, 2007), but these usually treat only a single aspect of context …

Content truncated to 500 words