Paper: Mapping between Compositional Semantic Representations and Lexical Semantic Resources: Towards Accurate Deep Semantic Parsing

ACL ID P08-2048
Title Mapping between Compositional Semantic Representations and Lexical Semantic Resources: Towards Accurate Deep Semantic Parsing
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2008
Authors
  • Sergio Roa (Saarland University, Saarbrucken Germany; German Research Center for Artificial Intelligence, Saarbrucken Germany; Freiburg University, Freiburg Germany)
  • Valia Kordoni (Saarland University, Saarbrucken Germany; German Research Center for Artificial Intelligence, Saarbrucken Germany)
  • Yi Zhang

This paper introduces a machine learning method based on bayesian networks which is applied to the mapping between deep se- mantic representations and lexical semantic resources. A probabilistic model comprising Minimal Recursion Semantics (MRS) struc- tures and lexicalist oriented semantic features is acquired. Lexical semantic roles enrich- ing the MRS structures are inferred, which are useful to improve the accuracy of deep seman- tic parsing. Verb classes inference was also investigated, which, together with lexical se- mantic information provided by VerbNet and PropBank resources, can be substantially ben- eficial to the parse disambiguation task.