Effective Broad-Coverage Deep Parsing

Authors

  • James Allen IHMC
  • Omid Bahkshandeh IHMC
  • William de Beaumont IHMC
  • Lucian Galescu IHMC
  • Choh Man Teng IHMC

DOI:

https://doi.org/10.1609/aaai.v32i1.11934

Keywords:

Natural Language Understanding, Parsing, Deep Parsing, Semantic Parsing

Abstract

Current semantic parsers either compute shallow representations over a wide range of input, or deeper representations in very limited domains. We describe a system that provides broad-coverage, deep semantic parsing designed to work in any domain using a core domain-general lexicon, ontology and grammar. This paper discusses how this core system can be customized for a particularly challenging domain, namely reading research papers in biology. We evaluate these customizations with some ablation experiments

AAAI 2018 Proceedings Cover

Downloads

Published

2018-04-26

How to Cite

Allen, J., Bahkshandeh, O., de Beaumont, W., Galescu, L., & Teng, C. M. (2018). Effective Broad-Coverage Deep Parsing. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). https://doi.org/10.1609/aaai.v32i1.11934

Issue

Vol. 32 No. 1 (2018): Thirty-Second AAAI Conference on Artificial Intelligence

Section

Main Track: NLP and Knowledge Representation