A Minimal Span-Based Neural Constituency Parser

@inproceedings{Stern2017AMS,
  title={A Minimal Span-Based Neural Constituency Parser},
  author={Mitchell Stern and Jacob Andreas and Dan Klein},
  booktitle={ACL},
  year={2017}
}
In this work, we present a minimal neural model for constituency parsing based on independent scoring of labels and spans. We show that this model is not only compatible with classical dynamic programming techniques, but also admits a novel greedy top-down inference algorithm based on recursive partitioning of the input. We demonstrate empirically that both prediction schemes are competitive with recent work, and when combined with basic extensions to the scoring model are capable of achieving… CONTINUE READING
Highly Cited
This paper has 29 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 20 times over the past 90 days. VIEW TWEETS

From This Paper

Figures, tables, results, and topics from this paper.

Key Quantitative Results

  • We demonstrate empirically that both prediction schemes are competitive with recent work, and when combined with basic extensions to the scoring model are capable of achieving state-of-the-art single-model performance on the Penn Treebank (91.79 F1) and strong performance on the French Treebank (82.23 F1).

Similar Papers

Loading similar papers…