@inproceedings{chou-etal-2023-advancing,
title = "Advancing Multi-Criteria {C}hinese Word Segmentation Through Criterion Classification and Denoising",
author = "Chou, Tzu Hsuan and
Lin, Chun-Yi and
Kao, Hung-Yu",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.356",
doi = "10.18653/v1/2023.acl-long.356",
pages = "6460--6476",
abstract = "Recent research on multi-criteria Chinese word segmentation (MCCWS) mainly focuses on building complex private structures, adding more handcrafted features, or introducing complex optimization processes. In this work, we show that through a simple yet elegant input-hint-based MCCWS model, we can achieve state-of-the-art (SoTA) performances on several datasets simultaneously. We further propose a novel criterion-denoising objective that hurts slightly on F1 score but achieves SoTA recall on out-of-vocabulary words. Our result establishes a simple yet strong baseline for future MCCWS research. Source code is available at \url{https://github.com/IKMLab/MCCWS}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chou-etal-2023-advancing">
<titleInfo>
<title>Advancing Multi-Criteria Chinese Word Segmentation Through Criterion Classification and Denoising</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tzu</namePart>
<namePart type="given">Hsuan</namePart>
<namePart type="family">Chou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chun-Yi</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hung-Yu</namePart>
<namePart type="family">Kao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent research on multi-criteria Chinese word segmentation (MCCWS) mainly focuses on building complex private structures, adding more handcrafted features, or introducing complex optimization processes. In this work, we show that through a simple yet elegant input-hint-based MCCWS model, we can achieve state-of-the-art (SoTA) performances on several datasets simultaneously. We further propose a novel criterion-denoising objective that hurts slightly on F1 score but achieves SoTA recall on out-of-vocabulary words. Our result establishes a simple yet strong baseline for future MCCWS research. Source code is available at https://github.com/IKMLab/MCCWS.</abstract>
<identifier type="citekey">chou-etal-2023-advancing</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.356</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.356</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>6460</start>
<end>6476</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Advancing Multi-Criteria Chinese Word Segmentation Through Criterion Classification and Denoising
%A Chou, Tzu Hsuan
%A Lin, Chun-Yi
%A Kao, Hung-Yu
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F chou-etal-2023-advancing
%X Recent research on multi-criteria Chinese word segmentation (MCCWS) mainly focuses on building complex private structures, adding more handcrafted features, or introducing complex optimization processes. In this work, we show that through a simple yet elegant input-hint-based MCCWS model, we can achieve state-of-the-art (SoTA) performances on several datasets simultaneously. We further propose a novel criterion-denoising objective that hurts slightly on F1 score but achieves SoTA recall on out-of-vocabulary words. Our result establishes a simple yet strong baseline for future MCCWS research. Source code is available at https://github.com/IKMLab/MCCWS.
%R 10.18653/v1/2023.acl-long.356
%U https://aclanthology.org/2023.acl-long.356
%U https://doi.org/10.18653/v1/2023.acl-long.356
%P 6460-6476
Markdown (Informal)
[Advancing Multi-Criteria Chinese Word Segmentation Through Criterion Classification and Denoising](https://aclanthology.org/2023.acl-long.356) (Chou et al., ACL 2023)
ACL