@inproceedings{shayegh-etal-2024-tree,
title = "Tree-Averaging Algorithms for Ensemble-Based Unsupervised Discontinuous Constituency Parsing",
author = "Shayegh, Behzad and
Wen, Yuqiao and
Mou, Lili",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.808",
doi = "10.18653/v1/2024.acl-long.808",
pages = "15135--15156",
abstract = "We address unsupervised discontinuous constituency parsing, where we observe a high variance in the performance of the only previous model in the literature. We propose to build an ensemble of different runs of the existing discontinuous parser by averaging the predicted trees, to stabilize and boost performance. To begin with, we provide comprehensive computational complexity analysis (in terms of P and NP-complete) for tree averaging under different setups of binarity and continuity. We then develop an efficient exact algorithm to tackle the task, which runs in a reasonable time for all samples in our experiments. Results on three datasets show our method outperforms all baselines in all metrics; we also provide in-depth analyses of our approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shayegh-etal-2024-tree">
<titleInfo>
<title>Tree-Averaging Algorithms for Ensemble-Based Unsupervised Discontinuous Constituency Parsing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Behzad</namePart>
<namePart type="family">Shayegh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuqiao</namePart>
<namePart type="family">Wen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lili</namePart>
<namePart type="family">Mou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We address unsupervised discontinuous constituency parsing, where we observe a high variance in the performance of the only previous model in the literature. We propose to build an ensemble of different runs of the existing discontinuous parser by averaging the predicted trees, to stabilize and boost performance. To begin with, we provide comprehensive computational complexity analysis (in terms of P and NP-complete) for tree averaging under different setups of binarity and continuity. We then develop an efficient exact algorithm to tackle the task, which runs in a reasonable time for all samples in our experiments. Results on three datasets show our method outperforms all baselines in all metrics; we also provide in-depth analyses of our approach.</abstract>
<identifier type="citekey">shayegh-etal-2024-tree</identifier>
<identifier type="doi">10.18653/v1/2024.acl-long.808</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.808</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>15135</start>
<end>15156</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Tree-Averaging Algorithms for Ensemble-Based Unsupervised Discontinuous Constituency Parsing
%A Shayegh, Behzad
%A Wen, Yuqiao
%A Mou, Lili
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F shayegh-etal-2024-tree
%X We address unsupervised discontinuous constituency parsing, where we observe a high variance in the performance of the only previous model in the literature. We propose to build an ensemble of different runs of the existing discontinuous parser by averaging the predicted trees, to stabilize and boost performance. To begin with, we provide comprehensive computational complexity analysis (in terms of P and NP-complete) for tree averaging under different setups of binarity and continuity. We then develop an efficient exact algorithm to tackle the task, which runs in a reasonable time for all samples in our experiments. Results on three datasets show our method outperforms all baselines in all metrics; we also provide in-depth analyses of our approach.
%R 10.18653/v1/2024.acl-long.808
%U https://aclanthology.org/2024.acl-long.808
%U https://doi.org/10.18653/v1/2024.acl-long.808
%P 15135-15156
Markdown (Informal)
[Tree-Averaging Algorithms for Ensemble-Based Unsupervised Discontinuous Constituency Parsing](https://aclanthology.org/2024.acl-long.808) (Shayegh et al., ACL 2024)
ACL