Abductive reasoning with a large knowledge base for discourse processing
Autor(en): | Ovchinnikova, E. Montazeri, N. Alexandrov, T. Hobbs, J.R. McCord, M.C. Mulkar-Mehta, R. |
Herausgeber: | Bos, J. Pulman, S. |
Stichwörter: | Knowledge based systems; Text processing, Abductive inference; Abductive reasoning; Discourse processing; Gold standards; Lexical semantics; Recognizing textual entailments; Semantic role labeling; Textual entailment, Semantics | Erscheinungsdatum: | 2011 | Herausgeber: | Association for Computational Linguistics, ACL Anthology | Journal: | Proceedings of the 9th International Conference on Computational Semantics, IWCS 2011 | Startseite: | 225 | Seitenende: | 234 | Zusammenfassung: | This paper presents a discourse processing framework based on weighted abduction. We elaborate on ideas described in Hobbs et al. (1993) and implement the abductive inference procedure in a system called Mini-TACITUS. Particular attention is paid to constructing a large and reliable knowledge base for supporting inferences. For this purpose we exploit such lexical-semantic resources as WordNet and FrameNet. We test the proposed procedure and the obtained knowledge base on the Recognizing Textual Entailment task using the data sets from the RTE-2 challenge for evaluation. In addition, we provide an evaluation of the semantic role labeling produced by the system taking the Frame-Annotated Corpus for Textual Entailment as a gold standard. |
Beschreibung: | Conference of 9th International Conference on Computational Semantics, IWCS 2011 ; Conference Date: 12 January 2011 Through 14 January 2011; Conference Code:131693 |
Externe URL: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-84949728525&partnerID=40&md5=3915e2456d4cbfbb59234d287352a742 |
Zur Langanzeige