@inproceedings{gong-etal-2020-multi,
title = "Multi-grained {C}hinese Word Segmentation with Weakly Labeled Data",
author = "Gong, Chen and
Li, Zhenghua and
Zou, Bowei and
Zhang, Min",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.183",
doi = "10.18653/v1/2020.coling-main.183",
pages = "2026--2036",
abstract = "In contrast with the traditional single-grained word segmentation (SWS), where a sentence corresponds to a single word sequence, multi-grained Chinese word segmentation (MWS) aims to segment a sentence into multiple word sequences to preserve all words of different granularities. Due to the lack of manually annotated MWS data, previous work train and tune MWS models only on automatically generated pseudo MWS data. In this work, we further take advantage of the rich word boundary information in existing SWS data and naturally annotated data from dictionary example (DictEx) sentences, to advance the state-of-the-art MWS model based on the idea of weak supervision. Particularly, we propose to accommodate two types of weakly labeled data for MWS, i.e., SWS data and DictEx data by employing a simple yet competitive graph-based parser with local loss. Besides, we manually annotate a high-quality MWS dataset according to our newly compiled annotation guideline, consisting of over 9,000 sentences from two types of texts, i.e., canonical newswire (NEWS) and non-canonical web (BAIKE) data for better evaluation. Detailed evaluation shows that our proposed model with weakly labeled data significantly outperforms the state-of-the-art MWS model by 1.12 and 5.97 on NEWS and BAIKE data in F1.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gong-etal-2020-multi">
<titleInfo>
<title>Multi-grained Chinese Word Segmentation with Weakly Labeled Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenghua</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bowei</namePart>
<namePart type="family">Zou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In contrast with the traditional single-grained word segmentation (SWS), where a sentence corresponds to a single word sequence, multi-grained Chinese word segmentation (MWS) aims to segment a sentence into multiple word sequences to preserve all words of different granularities. Due to the lack of manually annotated MWS data, previous work train and tune MWS models only on automatically generated pseudo MWS data. In this work, we further take advantage of the rich word boundary information in existing SWS data and naturally annotated data from dictionary example (DictEx) sentences, to advance the state-of-the-art MWS model based on the idea of weak supervision. Particularly, we propose to accommodate two types of weakly labeled data for MWS, i.e., SWS data and DictEx data by employing a simple yet competitive graph-based parser with local loss. Besides, we manually annotate a high-quality MWS dataset according to our newly compiled annotation guideline, consisting of over 9,000 sentences from two types of texts, i.e., canonical newswire (NEWS) and non-canonical web (BAIKE) data for better evaluation. Detailed evaluation shows that our proposed model with weakly labeled data significantly outperforms the state-of-the-art MWS model by 1.12 and 5.97 on NEWS and BAIKE data in F1.</abstract>
<identifier type="citekey">gong-etal-2020-multi</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.183</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.183</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>2026</start>
<end>2036</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-grained Chinese Word Segmentation with Weakly Labeled Data
%A Gong, Chen
%A Li, Zhenghua
%A Zou, Bowei
%A Zhang, Min
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F gong-etal-2020-multi
%X In contrast with the traditional single-grained word segmentation (SWS), where a sentence corresponds to a single word sequence, multi-grained Chinese word segmentation (MWS) aims to segment a sentence into multiple word sequences to preserve all words of different granularities. Due to the lack of manually annotated MWS data, previous work train and tune MWS models only on automatically generated pseudo MWS data. In this work, we further take advantage of the rich word boundary information in existing SWS data and naturally annotated data from dictionary example (DictEx) sentences, to advance the state-of-the-art MWS model based on the idea of weak supervision. Particularly, we propose to accommodate two types of weakly labeled data for MWS, i.e., SWS data and DictEx data by employing a simple yet competitive graph-based parser with local loss. Besides, we manually annotate a high-quality MWS dataset according to our newly compiled annotation guideline, consisting of over 9,000 sentences from two types of texts, i.e., canonical newswire (NEWS) and non-canonical web (BAIKE) data for better evaluation. Detailed evaluation shows that our proposed model with weakly labeled data significantly outperforms the state-of-the-art MWS model by 1.12 and 5.97 on NEWS and BAIKE data in F1.
%R 10.18653/v1/2020.coling-main.183
%U https://aclanthology.org/2020.coling-main.183
%U https://doi.org/10.18653/v1/2020.coling-main.183
%P 2026-2036
Markdown (Informal)
[Multi-grained Chinese Word Segmentation with Weakly Labeled Data](https://aclanthology.org/2020.coling-main.183) (Gong et al., COLING 2020)
ACL