Jointly Parse and Fragment Ungrammatical Sentences

Authors

  • Homa B. Hashemi University of Pittsburgh
  • Rebecca Hwa University of Pittsburgh

DOI:

https://doi.org/10.1609/aaai.v32i1.11998

Keywords:

Parse Tree Fragmentation, Dependency Arc Pruning, Ungrammatical Sentences, Semantic Role Labeling

Abstract

This paper is about detecting incorrect arcs in a dependency parse for sentences that contain grammar mistakes. Pruning these arcs results in well-formed parse fragments that can still be useful for downstream applications. We propose two automatic methods that jointly parse the ungrammatical sentence and prune the incorrect arcs: a parser retrained on a parallel corpus of ungrammatical sentences with their corrections, and a sequence-to-sequence method. Experimental results show that the proposed strategies are promising for detecting incorrect syntactic dependencies as well as incorrect semantic dependencies.

Downloads

Published

2018-04-27

How to Cite

B. Hashemi, H., & Hwa, R. (2018). Jointly Parse and Fragment Ungrammatical Sentences. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). https://doi.org/10.1609/aaai.v32i1.11998