English

Learning Syntax from Naturally-Occurring Bracketings

Computation and Language 2021-04-30 v1 Artificial Intelligence

Abstract

Naturally-occurring bracketings, such as answer fragments to natural language questions and hyperlinks on webpages, can reflect human syntactic intuition regarding phrasal boundaries. Their availability and approximate correspondence to syntax make them appealing as distant information sources to incorporate into unsupervised constituency parsing. But they are noisy and incomplete; to address this challenge, we develop a partial-brackets-aware structured ramp loss in learning. Experiments demonstrate that our distantly-supervised models trained on naturally-occurring bracketing data are more accurate in inducing syntactic structures than competing unsupervised systems. On the English WSJ corpus, our models achieve an unlabeled F1 score of 68.9 for constituency parsing.

Keywords

Cite

@article{arxiv.2104.13933,
  title  = {Learning Syntax from Naturally-Occurring Bracketings},
  author = {Tianze Shi and Ozan İrsoy and Igor Malioutov and Lillian Lee},
  journal= {arXiv preprint arXiv:2104.13933},
  year   = {2021}
}

Comments

NAACL 2021

R2 v1 2026-06-24T01:36:35.061Z