Building compositional semantics and higher-order inference system for a wide-coverage Japanese CCG parser

Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2236–2242, Austin, Texas, November 1-5, 2016. c⃝2016 Association for Computational Linguistics Building compositional semantics and higher-order inference system for a wide-coverage Japanese CCG parser Koji Mineshima1 mineshima.koji@ocha.ac.jp Ribeka Tanaka1 tanaka.ribeka@is.ocha.ac.jp Pascual Mart´ınez-G´omez2 pascual.mg@aist.go.jp Yusuke Miyao3 yusuke@nii.ac.jp Daisuke Bekki1 bekki@is.ocha.ac.jp 1Ochanomizu University Tokyo, Japan 2AIST Tokyo, Japan 3National Institute of Informatics The Graduate University for Advanced Studies Tokyo, Japan Abstract This paper presents a system that compo- sitionally maps outputs of a wide-coverage Japanese CCG parser onto semantic represen- tations and performs automated inference in higher-order logic. The system is evaluated on a textual entailment dataset. It is shown that the system solves inference problems that focus on a variety of complex linguistic phe- nomena, including those that are difficult to represent in the standard first-order logic. 1 Introduction Logic-based semantic representations have played an important role in the study of semantic parsing and inference. For English, several methods have been proposed to map outputs of parsers based on syntactic theories like CCG (Steedman, 2000) onto logical formulas (Bos, 2015). Output formulas have been used in various tasks, including Question An- swering (Lewis and Steedman, 2013) and Recog- nizing Textual Entailment (RTE) (Bos and Markert, 2005; Beltagy et al., 2013; Bjerva et al., 2014). Syntactic and semantic parsing for Japanese, by contrast, has been dominated by chunk-based de- pendency parsing and semantic role labelling (Kudo and Matsumoto, 2002; Kawahara and Kurohashi, 2011; Hayashibe et al., 2011). Recently, the method of inducing wide-coverage CCG resources for En- glish (Hockenmaier and Steedman, 2007) has been applied to Japanese and a robust CCG parser based on it has been developed (Uematsu et al., 2015). However, building a method to map CCG trees in Japanese onto logical formulas is not a trivial task, mainly due to the differences in syntactic structures between English and Japanese (Section 3). per.There are two primary contributions of this pa- First, based on an in-depth analysis of the syntax-semantics interface in Japanese, we present the first system that compositionally derives seman- tic representations for a wide-coverage Japanese CCG parser. Output representations are formulas in higher-order logic (HOL) combined with Neo- Davidsonian Event Semantics (Parsons, 1990). Sec- ond, we demonstrate the capacity of HOL for textual entailment. We evaluate the system on a Japanese textual entailment dataset (Kawazoe et al., 2015), a dataset constructed in a similar way to the FraCaS dataset for English (Cooper et al., 1994; MacCartney and Manning, 2007). Although it is usually thought that HOL is unfeasible for practical applications, the results show that the entire system is able to perform efficient logical inference on complex linguistic phe- nomena such as generalized quantifiers and inten- sional modifiers — phenomena that pose challenges to the standard first-order-logic-based approaches. 2 Background and system overview This section provides a brief overview of the en- tire system as applied to RTE, a task of determin- ing whether a given text (T) entails, contradicts, or is just consistent with, …

Content truncated to 500 words