Discourse Representation Structure Parsing
2018pp. 429–439
Citations Over TimeTop 10% of 2018 papers
Abstract
We introduce an open-domain neural semantic parser which generates formal meaning representations in the style of Discourse Representation Theory (DRT; Kamp and Reyle 1993). We propose a method which transforms Discourse Representation Structures (DRSs) to trees and develop a structure-aware model which decomposes the decoding process into three stages: basic DRS structure prediction, condition prediction (i.e., predicates and relations), and referent prediction (i.e., variables). Experimental results on the Groningen Meaning Bank (GMB) show that our model outperforms competitive baselines by a wide margin.
Related Papers
- → What’s new? Children prefer novelty in referent selection(2010)105 cited
- → Referent Networks and Distributive Justice(2014)8 cited
- → Formal and informal referent groups: an exploration of novices and experts in maternity services(2001)8 cited
- → Co-operation in research in Europe(1959)
- Who Is the Pioneer?——On the Changes of the Concept of Pioneer(2004)