UIO-Lien: Entailment Recognition using Minimal Recursion Semantics

Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), pages 699–703, Dublin, Ireland, August 23-24, 2014. UIO-Lien: Entailment Recognition using Minimal Recursion Semantics Elisabeth Lien Department of Informatics University of Oslo, Norway elien@ifi.uio.no Milen Kouylekov Department of Informatics University of Oslo, Norway milen@ifi.uio.no Abstract In this paper we present our participa- tion in the Semeval 2014 task “Evalu- ation of compositional distributional se- mantic models on full sentences through semantic relatedness and textual entail- ment”. Our results demonstrate that us- ing generic tools for semantic analysis is a viable option for a system that recognizes textual entailment. The invested effort in developing such tools allows us to build systems for reasoning that do not require training. 1 Introduction Recognizing textual entailment (RTE) has been a popular area of research in the last years. It has appeared in a variety of evaluation campaigns as both monolingual and multilingual tasks. A wide variety of techniques based on different levels of text interpretation has been used, e.g., lexical dis- tance, dependency parsing and semantic role la- beling (Androutsopoulos and Malakasiotis, 2010). Our approach uses a semantic representation formalism called Minimal Recursion Semantics (MRS), which, to our knowledge, has not been used extensively in entailment decision systems. Notable examples of systems that use MRS are Wotzlaw and Coote (2013), and Bergmair (2010). In Wotzlaw and Coote (2013), the authors present an entailment recognition system which combines high-coverage syntactic and semantic text analysis with logical inference supported by relevant back- ground knowledge. MRS is used as an interme- diate format in transforming the results of the lin- guistic analysis into representations used for log- ical reasoning. The approach in Bergmair (2010) This work is licensed under a Creative Commons At- tribution 4.0 International Licence. Page numbers and pro- ceedings footer are added by the organisers. Licence details: http://creativecommons.org/licenses/by/4.0/ uses the syllogism as an approximation of natural language reasoning. MRS is used as a step in the translation of natural language sentences into logi- cal formulae that are suitable for processing. Both works describe approaches that can be adapted to RTE, but no empirical evaluation is included to demonstrate the potential of the proposed ap- proaches. In contrast to these approaches, our system bases entailment decision directly on the MRS representations. Graph alignment over MRS rep- resentations forms the basis for entailment recog- nition. If key nodes in the hypothesis MRS can be aligned to nodes in the text MRS, this is treated as an indicator of entailment. This paper represents our first attempt to evalu- ate a system based on logical-form semantic rep- resentations in a RTE competition. Using a state- of-the-art semantic analysis component, we have created a generic rule-based system for recogniz- ing textual entailment that obtains competitive re- sults on a real evaluation dataset. Our approach does not require training. We confront it with a strong baseline provided by the EDITS system (Kouylekov et al., 2011). In Section 2 we describe the computational se- mantics framework that forms the basis …

Content truncated to 500 words