Simple Robust Grammar Induction with Combinatory Categorial Grammars

Authors

  • Yonatan Bisk University of Illinois at Urbana-Champaign
  • Julia Hockenmaier University of Illinois at Urbana-Champaign

DOI:

https://doi.org/10.1609/aaai.v26i1.8355

Keywords:

Combinatory Categorial Grammar, Grammar Induction

Abstract

We present a simple EM-based grammar induction algorithm for Combinatory Categorial Grammar (CCG) that achieves state-of-the-art performance by relying on a minimal number of very general linguistic principles. Unlike previous work on unsupervised parsing with CCGs, our approach has no prior language-specific knowledge, and discovers all categories automatically. Additionally, unlike other approaches, our grammar remains robust when parsing longer sentences, performing as well as or better than other systems. We believe this is a natural result of using an expressive grammar formalism with an extended domain of locality.

Downloads

Published

2021-09-20

How to Cite

Bisk, Y., & Hockenmaier, J. (2021). Simple Robust Grammar Induction with Combinatory Categorial Grammars. Proceedings of the AAAI Conference on Artificial Intelligence, 26(1), 1643-1649. https://doi.org/10.1609/aaai.v26i1.8355

Issue

Section

AAAI Technical Track: Natural Language Processing