@inproceedings{gomez-rodriguez-vilares-2018-constituent,
title = "Constituent Parsing as Sequence Labeling",
author = "G{\'o}mez-Rodr{\'\i}guez, Carlos and
Vilares, David",
editor = "Riloff, Ellen and
Chiang, David and
Hockenmaier, Julia and
Tsujii, Jun{'}ichi",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
month = oct # "-" # nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D18-1162",
doi = "10.18653/v1/D18-1162",
pages = "1314--1324",
abstract = "We introduce a method to reduce constituent parsing to sequence labeling. For each word $w_t$, it generates a label that encodes: (1) the number of ancestors in the tree that the words $w_t$ and $w_{t+1}$ have in common, and (2) the nonterminal symbol at the lowest common ancestor. We first prove that the proposed encoding function is injective for any tree without unary branches. In practice, the approach is made extensible to all constituency trees by collapsing unary branches. We then use the PTB and CTB treebanks as testbeds and propose a set of fast baselines. We achieve 90{\%} F-score on the PTB test set, outperforming the Vinyals et al. (2015) sequence-to-sequence parser. In addition, sacrificing some accuracy, our approach achieves the fastest constituent parsing speeds reported to date on PTB by a wide margin.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gomez-rodriguez-vilares-2018-constituent">
<titleInfo>
<title>Constituent Parsing as Sequence Labeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="family">Gómez-Rodríguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Vilares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-oct-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ellen</namePart>
<namePart type="family">Riloff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Chiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Hockenmaier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun’ichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce a method to reduce constituent parsing to sequence labeling. For each word w_t, it generates a label that encodes: (1) the number of ancestors in the tree that the words w_t and w_t+1 have in common, and (2) the nonterminal symbol at the lowest common ancestor. We first prove that the proposed encoding function is injective for any tree without unary branches. In practice, the approach is made extensible to all constituency trees by collapsing unary branches. We then use the PTB and CTB treebanks as testbeds and propose a set of fast baselines. We achieve 90% F-score on the PTB test set, outperforming the Vinyals et al. (2015) sequence-to-sequence parser. In addition, sacrificing some accuracy, our approach achieves the fastest constituent parsing speeds reported to date on PTB by a wide margin.</abstract>
<identifier type="citekey">gomez-rodriguez-vilares-2018-constituent</identifier>
<identifier type="doi">10.18653/v1/D18-1162</identifier>
<location>
<url>https://aclanthology.org/D18-1162</url>
</location>
<part>
<date>2018-oct-nov</date>
<extent unit="page">
<start>1314</start>
<end>1324</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Constituent Parsing as Sequence Labeling
%A Gómez-Rodríguez, Carlos
%A Vilares, David
%Y Riloff, Ellen
%Y Chiang, David
%Y Hockenmaier, Julia
%Y Tsujii, Jun’ichi
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F gomez-rodriguez-vilares-2018-constituent
%X We introduce a method to reduce constituent parsing to sequence labeling. For each word w_t, it generates a label that encodes: (1) the number of ancestors in the tree that the words w_t and w_t+1 have in common, and (2) the nonterminal symbol at the lowest common ancestor. We first prove that the proposed encoding function is injective for any tree without unary branches. In practice, the approach is made extensible to all constituency trees by collapsing unary branches. We then use the PTB and CTB treebanks as testbeds and propose a set of fast baselines. We achieve 90% F-score on the PTB test set, outperforming the Vinyals et al. (2015) sequence-to-sequence parser. In addition, sacrificing some accuracy, our approach achieves the fastest constituent parsing speeds reported to date on PTB by a wide margin.
%R 10.18653/v1/D18-1162
%U https://aclanthology.org/D18-1162
%U https://doi.org/10.18653/v1/D18-1162
%P 1314-1324
Markdown (Informal)
[Constituent Parsing as Sequence Labeling](https://aclanthology.org/D18-1162) (Gómez-Rodríguez & Vilares, EMNLP 2018)
ACL
- Carlos Gómez-Rodríguez and David Vilares. 2018. Constituent Parsing as Sequence Labeling. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 1314–1324, Brussels, Belgium. Association for Computational Linguistics.