@inproceedings{tang-etal-2023-ji,
title = "基于词向量的自适应领域术语抽取方法(An Adaptive Domain-Specific Terminology Extraction Approach Based on Word Embedding)",
author = "Tang, Xi and
Jiang, Dongchen and
Jiang, Aoyuan",
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-1.17",
pages = "186--195",
abstract = "{``}术语分布呈现长尾特性。为了有效提取低频术语,本文提出了一种基于词向量的自适应术语抽取方法。该方法使用基于假设检验的统计方法,自适应地确定筛选阈值,通过逐步合并文本的强关联性字符串获得候选术语,避免了因固定阈值导致的低频术语遗漏问题;其后,本文基于掩码语言模型获得未登录候选术语的词向量,并通过融合词典知识的密度聚类算法获得候选术语归属的领域簇,将归属于目标领域簇的候选术语认定为领域术语。实验结果表明,我们的方法不仅在但值上优于对比方法,而且在不同体裁的文本中表现更为稳定。该方法能够全面有效地抽取出低频术语,实现领域术语的高质量提取。{''}",
language = "Chinese",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tang-etal-2023-ji">
<titleInfo>
<title>基于词向量的自适应领域术语抽取方法(An Adaptive Domain-Specific Terminology Extraction Approach Based on Word Embedding)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xi</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongchen</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aoyuan</namePart>
<namePart type="family">Jiang</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>“术语分布呈现长尾特性。为了有效提取低频术语,本文提出了一种基于词向量的自适应术语抽取方法。该方法使用基于假设检验的统计方法,自适应地确定筛选阈值,通过逐步合并文本的强关联性字符串获得候选术语,避免了因固定阈值导致的低频术语遗漏问题;其后,本文基于掩码语言模型获得未登录候选术语的词向量,并通过融合词典知识的密度聚类算法获得候选术语归属的领域簇,将归属于目标领域簇的候选术语认定为领域术语。实验结果表明,我们的方法不仅在但值上优于对比方法,而且在不同体裁的文本中表现更为稳定。该方法能够全面有效地抽取出低频术语,实现领域术语的高质量提取。”</abstract>
<identifier type="citekey">tang-etal-2023-ji</identifier>
<location>
<url>https://aclanthology.org/2023.ccl-1.17</url>
</location>
<part>
<date>2023-08</date>
<extent unit="page">
<start>186</start>
<end>195</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T 基于词向量的自适应领域术语抽取方法(An Adaptive Domain-Specific Terminology Extraction Approach Based on Word Embedding)
%A Tang, Xi
%A Jiang, Dongchen
%A Jiang, Aoyuan
%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 tang-etal-2023-ji
%X “术语分布呈现长尾特性。为了有效提取低频术语,本文提出了一种基于词向量的自适应术语抽取方法。该方法使用基于假设检验的统计方法,自适应地确定筛选阈值,通过逐步合并文本的强关联性字符串获得候选术语,避免了因固定阈值导致的低频术语遗漏问题;其后,本文基于掩码语言模型获得未登录候选术语的词向量,并通过融合词典知识的密度聚类算法获得候选术语归属的领域簇,将归属于目标领域簇的候选术语认定为领域术语。实验结果表明,我们的方法不仅在但值上优于对比方法,而且在不同体裁的文本中表现更为稳定。该方法能够全面有效地抽取出低频术语,实现领域术语的高质量提取。”
%U https://aclanthology.org/2023.ccl-1.17
%P 186-195
Markdown (Informal)
[基于词向量的自适应领域术语抽取方法(An Adaptive Domain-Specific Terminology Extraction Approach Based on Word Embedding)](https://aclanthology.org/2023.ccl-1.17) (Tang et al., CCL 2023)
ACL