@article{roca-etal-2026-sequence,
title = "Sequence Labeling for Constituent Parsing: A Comparative Study and Encoding Innovations",
author = "Roca, Diego and
Vilares, David and
G{\'o}mez-Rodr{\'i}guez, Carlos",
journal = "Computational Linguistics",
volume = "52",
number = "2",
month = jun,
year = "2026",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/2026.cl-2.3/",
doi = "10.1162/coli.a.603",
pages = "495--539",
abstract = "Various encodings have been proposed to cast constituent parsing in terms of a sequence labeling task. However, unlike in the case of dependency parsing, existing comparisons have not been entirely homogeneous and, to the best of our knowledge, there is no systematic evaluation of these encodings under uniform configurations. A homogeneous evaluation needs to account for various aspects that could influence results, either by controlling for these aspects to ensure uniformity (e.g., network architecture, parameter settings, postprocessing of ill-formed output), or by systematically analyzing their impact (e.g., the impact of binary versus arbitrary structures). In this article, we: (1) compare different encodings comprehensively both theoretically and empirically, on a modern neural architecture and across nine languages, and (2) introduce new encodings and variants, including an encoding that our analysis finds particularly accurate and compact."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="roca-etal-2026-sequence">
<titleInfo>
<title>Sequence Labeling for Constituent Parsing: A Comparative Study and Encoding Innovations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Diego</namePart>
<namePart type="family">Roca</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>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="family">Gómez-Rodríguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>Various encodings have been proposed to cast constituent parsing in terms of a sequence labeling task. However, unlike in the case of dependency parsing, existing comparisons have not been entirely homogeneous and, to the best of our knowledge, there is no systematic evaluation of these encodings under uniform configurations. A homogeneous evaluation needs to account for various aspects that could influence results, either by controlling for these aspects to ensure uniformity (e.g., network architecture, parameter settings, postprocessing of ill-formed output), or by systematically analyzing their impact (e.g., the impact of binary versus arbitrary structures). In this article, we: (1) compare different encodings comprehensively both theoretically and empirically, on a modern neural architecture and across nine languages, and (2) introduce new encodings and variants, including an encoding that our analysis finds particularly accurate and compact.</abstract>
<identifier type="citekey">roca-etal-2026-sequence</identifier>
<identifier type="doi">10.1162/coli.a.603</identifier>
<location>
<url>https://aclanthology.org/2026.cl-2.3/</url>
</location>
<part>
<date>2026-06</date>
<detail type="volume"><number>52</number></detail>
<detail type="issue"><number>2</number></detail>
<extent unit="page">
<start>495</start>
<end>539</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Sequence Labeling for Constituent Parsing: A Comparative Study and Encoding Innovations
%A Roca, Diego
%A Vilares, David
%A Gómez-Rodríguez, Carlos
%J Computational Linguistics
%D 2026
%8 June
%V 52
%N 2
%I MIT Press
%C Cambridge, MA
%F roca-etal-2026-sequence
%X Various encodings have been proposed to cast constituent parsing in terms of a sequence labeling task. However, unlike in the case of dependency parsing, existing comparisons have not been entirely homogeneous and, to the best of our knowledge, there is no systematic evaluation of these encodings under uniform configurations. A homogeneous evaluation needs to account for various aspects that could influence results, either by controlling for these aspects to ensure uniformity (e.g., network architecture, parameter settings, postprocessing of ill-formed output), or by systematically analyzing their impact (e.g., the impact of binary versus arbitrary structures). In this article, we: (1) compare different encodings comprehensively both theoretically and empirically, on a modern neural architecture and across nine languages, and (2) introduce new encodings and variants, including an encoding that our analysis finds particularly accurate and compact.
%R 10.1162/coli.a.603
%U https://aclanthology.org/2026.cl-2.3/
%U https://doi.org/10.1162/coli.a.603
%P 495-539
Markdown (Informal)
[Sequence Labeling for Constituent Parsing: A Comparative Study and Encoding Innovations](https://aclanthology.org/2026.cl-2.3/) (Roca et al., CL 2026)
ACL