Incremental Semantic Construction Using Normal Form CCG Derivation

Proceedings of the Fourth Joint Conference on Lexical and Computational Semantics (*SEM 2015), pages 269–278, Denver, Colorado, June 4–5, 2015. Incremental Semantic Construction Using Normal Form CCG Derivation Yoshihide Kato1 and Shigeki Matsubara2 1Information & Communications, Nagoya University 2Graduate School of Information Science, Nagoya University Furo-cho, Chikusa-ku, Nagoya, 464-8601 Japan yoshihide@icts.nagoya-u.ac.jp Abstract This paper proposes a method of incremen- tally constructing semantic representations. Our method is based on Steedman’s Combina- tory Categorial Grammar (CCG), which has a transparent correspondence between the syn- tax and semantics. In our method, a derivation for a sentence is constructed in an incremen- tal fashion and the corresponding semantic representation is derived synchronously. Our method uses normal form CCG derivation. This is the difference between our approach and previous ones. Previous approaches use most left-branching derivation called incre- mental derivation, but they cannot process co- ordinate structures incrementally. Our method overcomes this problem. 1 Introduction By incremental interpretation, we mean that a sen- tence is analyzed from left to right, and a semantic representation is assigned to each initial fragment of the sentence. These properties enable NLP systems to analyze unfinished sentences. Moreover, incre- mental interpretation is useful for incremental dia- logue systems (Allen et al., 2001; Aist et al., 2007; Purver et al., 2011; Peldszus and Schlangen, 2012). Furthermore, in the field of psycholinguistics, incre- mental interpretation has been explored as a human sentence processing model. This paper proposes a method of constructing a semantic representation for each initial fragment of a sentence in an incremental fashion. The proposed method is based on Combinatory Categorial Gram- mar (CCG) (Steedman, 2000). CCG represents the syntactic process as a derivation which is a tree structure. Our method constructs a CCG derivation by applying operations used in incremental phrase structure parsing. Each intermediate data structure constructed by the operations represents partial in- formation of some derivation. Our method obtains a semantic representation from the intermediate struc- ture. Since the obtained semantic representations conform to the CCG semantic construction, we can expect that incremental semantic interpretation is re- alized by applying a CCG-based semantic analysis such as (Bos, 2008). This paper is organized as follows: Section 2 briefly explains Combinatory Categorial Gram- mar. Section 3 gives an overview of previous work of CCG-based incremental parsing and discusses its problem. Section 4 proposes our CCG-based method of incrementally constructing semantic rep- resentations. Section 5 reviews related work and Section 6 concludes this paper. 2 Combinatory Categorial Grammar Combinatory Categorial Grammar (CCG) (Steed- man, 2000) is a grammar formalism which has a transparent correspondence between the syntax and semantics. Syntactic information is represented us- ing basic categories (e.g., S, NP) and complex cate- gories. Complex categories are in the form of X/Y or X\Y , where X and Y are categories. Intuitively, each category in the form of X/Y means that it re- ceives a category Y from its right and returns a cat- egory X. In the case of the form X\Y , the direc- tion is to left. …

Content truncated to 500 words