The State of the Art in Semantic Representation

Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, pages 77–89 Vancouver, Canada, July 30 - August 4, 2017. c⃝2017 Association for Computational Linguistics https://doi.org/10.18653/v1/P17-1008 Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, pages 77–89 Vancouver, Canada, July 30 - August 4, 2017. c⃝2017 Association for Computational Linguistics https://doi.org/10.18653/v1/P17-1008 The State of the Art in Semantic Representation Omri Abend Ari Rappoport Department of Computer Science, The Hebrew University of Jerusalem {oabend|arir}@cs.huji.ac.il Abstract Semantic representation is receiving grow- ing attention in NLP in the past few years, and many proposals for semantic schemes (e.g., AMR, UCCA, GMB, UDS) have been put forth. Yet, little has been done to assess the achievements and the shortcom- ings of these new contenders, compare them with syntactic schemes, and clarify the general goals of research on semantic representation. We address these gaps by critically surveying the state of the art in the field. 1 Introduction Schemes for Semantic Representation of Text (SRT) aim to reflect the meaning of sentences and texts in a transparent way. There has recently been an influx of proposals for semantic representa- tions and corpora, e.g. GMB (Basile et al., 2012), AMR (Banarescu et al., 2013), UCCA (Abend and Rappoport, 2013b) and Universal Decomposi- tional Semantics (UDS; White et al., 2016). Nev- ertheless, no detailed assessment of the relative merits of the different schemes has been carried out, nor their comparison to previous sentential analysis schemes, notably syntactic ones. An un- derstanding of the achievements and gaps of se- mantic analysis in NLP is crucial to its future prospects. In this paper we begin to chart the various pro- posals for semantic schemes according to the con- tent they support. As not many semantic queries on texts can at present be answered with near human-like reliability without using manual sym- bolic annotation, we will mostly focus on schemes that represent semantic distinctions explicitly.1 We begin by discussing the goals of SRT in Sec- tion 2. Section 3 surveys major represented mean- ing components, including predicate-argument re- lations, discourse relations and logical structure. Section 4 details the various concrete proposals for SRT schemes and annotated resources, while Sec- tions 5 and 6 discuss criteria for their evaluation and their relation to syntax, respectively. We find that despite the major differences in terms of formalism and interface with syntax, in terms of their content there is a great deal of con- vergence of SRT schemes. Principal differences between schemes are mostly related to their ability to abstract away from formal and syntactic vari- ation, namely to assign similar structures to dif- ferent constructions that have a similar meaning, and to assign different structures to constructions that have different meanings, despite their surface similarity. Other important differences are in the level of training they require from their annota- tors (e.g., expert annotators vs. crowd-sourcing) and in their cross-linguistic generality. We discuss the complementary strengths of different schemes, and suggest paths for future integration. 2 Defining Semantic Representation …

Content truncated to 500 words