tailieunhanh - Báo cáo khoa học: "Automatic learning of textual entailments with cross-pair similarities"

In this paper we define a novel similarity measure between examples of textual entailments and we use it as a kernel function in Support Vector Machines (SVMs). This allows us to automatically learn the rewrite rules that describe a non trivial set of entailment cases. The experiments with the data sets of the RTE 2005 challenge show an improvement of over the state-of-the-art methods. | Automatic learning of textual entailments with cross-pair similarities Fabio Massimo Zanzotto DISCo University of Milano-Bicocca Milan Italy zanzotto@ Alessandro Moschitti Department of Computer Science University of Rome Tor Vergata Rome Italy moschitti@ Abstract In this paper we define a novel similarity measure between examples of textual entailments and we use it as a kernel function in Support Vector Machines SVMs . This allows us to automatically learn the rewrite rules that describe a non trivial set of entailment cases. The experiments with the data sets of the RTE 2005 challenge show an improvement of over the state-of-the-art methods. 1 Introduction Recently textual entailment recognition has been receiving a lot of attention. The main reason is that the understanding of the basic entailment processes will allow us to model more accurate semantic theories of natural languages Chierchia and McConnell-Ginet 2001 and design important applications Dagan and Glickman 2004 . Question Answering and Information Extraction. However previous work . Zaenen et al. 2005 suggests that determining whether or not a text T entails a hypothesis H is quite complex even when all the needed information is explicitly asserted. For example the sentence T1 At the end of the year all solid companies pay dividends. entails the hypothesis H1 At the end of the year all solid insurance companies pay dividends. but it does not entail the hypothesis H2 At the end of the year all solid companies pay cash dividends. Although these implications are uncontrover-sial their automatic recognition is complex if we rely on models based on lexical distance or similarity between hypothesis and text . Corley and Mihalcea 2005 . Indeed according to such approaches the hypotheses Hl and H2 are very similar and seem to be similarly related to T1. This suggests that we should study the properties and differences of such two examples negative and positive to