Better, Faster, Stronger Sequence Tagging Constituent Parsers

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Standard

Better, Faster, Stronger Sequence Tagging Constituent Parsers. / Vilares, David; Abdou, Mostafa; Søgaard, Anders.

Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Association for Computational Linguistics, 2019. p. 3372-3383.

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Harvard

Vilares, D, Abdou, M & Søgaard, A 2019, Better, Faster, Stronger Sequence Tagging Constituent Parsers. in Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Association for Computational Linguistics, pp. 3372-3383, 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - NAACL-HLT 2019, Minneapolis, United States, 03/06/2019. https://doi.org/10.18653/v1/N19-1341

APA

Vilares, D., Abdou, M., & Søgaard, A. (2019). Better, Faster, Stronger Sequence Tagging Constituent Parsers. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) (pp. 3372-3383). Association for Computational Linguistics. https://doi.org/10.18653/v1/N19-1341

Vancouver

Vilares D, Abdou M, Søgaard A. Better, Faster, Stronger Sequence Tagging Constituent Parsers. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Association for Computational Linguistics. 2019. p. 3372-3383 https://doi.org/10.18653/v1/N19-1341

Author

Vilares, David ; Abdou, Mostafa ; Søgaard, Anders. / Better, Faster, Stronger Sequence Tagging Constituent Parsers. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Association for Computational Linguistics, 2019. pp. 3372-3383

Bibtex

@inproceedings{f8d3cfc8dd244ab399704e11741c4090,
title = "Better, Faster, Stronger Sequence Tagging Constituent Parsers",
abstract = "Sequence tagging models for constituent parsing are faster, but less accurate than other types of parsers. In this work, we address the following weaknesses of such constituent parsers: (a) high error rates around closing brackets of long constituents, (b) large label sets, leading to sparsity, and (c) error propagation arising from greedy decoding. To effectively close brackets, we train a model that learns to switch between tagging schemes. To reduce sparsity, we decompose the label set and use multi-task learning to jointly learn to predict sublabels. Finally, we mitigate issues from greedy decoding through auxiliary losses and sentence-level fine-tuning with policy gradient. Combining these techniques, we clearly surpass the performance of sequence tagging constituent parsers on the English and Chinese Penn Treebanks, and reduce their parsing time even further. On the SPMRL datasets, we observe even greater improvements across the board, including a new state of the art on Basque, Hebrew, Polish and Swedish.",
author = "David Vilares and Mostafa Abdou and Anders S{\o}gaard",
year = "2019",
doi = "10.18653/v1/N19-1341",
language = "English",
pages = "3372--3383",
booktitle = "Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
publisher = "Association for Computational Linguistics",
note = "2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - NAACL-HLT 2019 ; Conference date: 03-06-2019 Through 07-06-2019",

}

RIS

TY - GEN

T1 - Better, Faster, Stronger Sequence Tagging Constituent Parsers

AU - Vilares, David

AU - Abdou, Mostafa

AU - Søgaard, Anders

PY - 2019

Y1 - 2019

N2 - Sequence tagging models for constituent parsing are faster, but less accurate than other types of parsers. In this work, we address the following weaknesses of such constituent parsers: (a) high error rates around closing brackets of long constituents, (b) large label sets, leading to sparsity, and (c) error propagation arising from greedy decoding. To effectively close brackets, we train a model that learns to switch between tagging schemes. To reduce sparsity, we decompose the label set and use multi-task learning to jointly learn to predict sublabels. Finally, we mitigate issues from greedy decoding through auxiliary losses and sentence-level fine-tuning with policy gradient. Combining these techniques, we clearly surpass the performance of sequence tagging constituent parsers on the English and Chinese Penn Treebanks, and reduce their parsing time even further. On the SPMRL datasets, we observe even greater improvements across the board, including a new state of the art on Basque, Hebrew, Polish and Swedish.

AB - Sequence tagging models for constituent parsing are faster, but less accurate than other types of parsers. In this work, we address the following weaknesses of such constituent parsers: (a) high error rates around closing brackets of long constituents, (b) large label sets, leading to sparsity, and (c) error propagation arising from greedy decoding. To effectively close brackets, we train a model that learns to switch between tagging schemes. To reduce sparsity, we decompose the label set and use multi-task learning to jointly learn to predict sublabels. Finally, we mitigate issues from greedy decoding through auxiliary losses and sentence-level fine-tuning with policy gradient. Combining these techniques, we clearly surpass the performance of sequence tagging constituent parsers on the English and Chinese Penn Treebanks, and reduce their parsing time even further. On the SPMRL datasets, we observe even greater improvements across the board, including a new state of the art on Basque, Hebrew, Polish and Swedish.

U2 - 10.18653/v1/N19-1341

DO - 10.18653/v1/N19-1341

M3 - Article in proceedings

SP - 3372

EP - 3383

BT - Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

PB - Association for Computational Linguistics

T2 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - NAACL-HLT 2019

Y2 - 3 June 2019 through 7 June 2019

ER -

ID: 240419283