@inproceedings{yan-etal-2023-ji,
title = "基于网络词典的现代汉语词义消歧数据集构建(Construction of a {M}odern {C}hinese Word Sense Dataset Based on Online Dictionaries)",
author = "Yan, Fukang and
Zhang, Yue and
Li, Zhenghua",
editor = "Sun, Maosong and
Qin, Bing and
Qiu, Xipeng and
Jiang, Jing and
Han, Xianpei",
booktitle = "Proceedings of the 22nd Chinese National Conference on Computational Linguistics",
month = aug,
year = "2023",
address = "Harbin, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2023.ccl-1.4",
pages = "43--53",
abstract = "{``}词义消歧作为自然语言处理最经典的任务之一,旨在识别多义词在给定上下文中的正确词义。相比英文,中文的一词多义现象更普遍,然而当前公开发布的汉语词义消歧数据集很少。本文爬取并融合了两个公开的网络词典,并从中筛选1083个词语和相关义项作为待标注对象。进而,从网络数据及专业语料中为抽取相关句子。最后,以多人标注、专家审核的方式进行了人工标注。数据集1包含将近2万个句子,即每个词平均对应约20个句子。本文将数据集划分为训练集、验证集和测试集,对多种模型进行实验对比。{''}",
language = "Chinese",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yan-etal-2023-ji">
<titleInfo>
<title>基于网络词典的现代汉语词义消歧数据集构建(Construction of a Modern Chinese Word Sense Dataset Based on Online Dictionaries)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fukang</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</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>
<originInfo>
<dateIssued>2023-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">Chinese</languageTerm>
<languageTerm type="code" authority="iso639-2b">chi</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd Chinese National Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xipeng</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianpei</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Harbin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>“词义消歧作为自然语言处理最经典的任务之一,旨在识别多义词在给定上下文中的正确词义。相比英文,中文的一词多义现象更普遍,然而当前公开发布的汉语词义消歧数据集很少。本文爬取并融合了两个公开的网络词典,并从中筛选1083个词语和相关义项作为待标注对象。进而,从网络数据及专业语料中为抽取相关句子。最后,以多人标注、专家审核的方式进行了人工标注。数据集1包含将近2万个句子,即每个词平均对应约20个句子。本文将数据集划分为训练集、验证集和测试集,对多种模型进行实验对比。”</abstract>
<identifier type="citekey">yan-etal-2023-ji</identifier>
<location>
<url>https://aclanthology.org/2023.ccl-1.4</url>
</location>
<part>
<date>2023-08</date>
<extent unit="page">
<start>43</start>
<end>53</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T 基于网络词典的现代汉语词义消歧数据集构建(Construction of a Modern Chinese Word Sense Dataset Based on Online Dictionaries)
%A Yan, Fukang
%A Zhang, Yue
%A Li, Zhenghua
%Y Sun, Maosong
%Y Qin, Bing
%Y Qiu, Xipeng
%Y Jiang, Jing
%Y Han, Xianpei
%S Proceedings of the 22nd Chinese National Conference on Computational Linguistics
%D 2023
%8 August
%I Chinese Information Processing Society of China
%C Harbin, China
%G Chinese
%F yan-etal-2023-ji
%X “词义消歧作为自然语言处理最经典的任务之一,旨在识别多义词在给定上下文中的正确词义。相比英文,中文的一词多义现象更普遍,然而当前公开发布的汉语词义消歧数据集很少。本文爬取并融合了两个公开的网络词典,并从中筛选1083个词语和相关义项作为待标注对象。进而,从网络数据及专业语料中为抽取相关句子。最后,以多人标注、专家审核的方式进行了人工标注。数据集1包含将近2万个句子,即每个词平均对应约20个句子。本文将数据集划分为训练集、验证集和测试集,对多种模型进行实验对比。”
%U https://aclanthology.org/2023.ccl-1.4
%P 43-53
Markdown (Informal)
[基于网络词典的现代汉语词义消歧数据集构建(Construction of a Modern Chinese Word Sense Dataset Based on Online Dictionaries)](https://aclanthology.org/2023.ccl-1.4) (Yan et al., CCL 2023)
ACL