@inproceedings{sijia-etal-2024-nnp,
title = "{NNP}-{TDGM}: 基于最近邻提示表征的术语{DEF}生成模型({NNP}-{TDGM}: Nearest Neighbor Prompt Term {DEF} Generation Model)",
author = "Shen, Sijia and
Wang, Peiyan and
Wang, Shengren and
Wang, Libang",
editor = "Maosong, Sun and
Jiye, Liang and
Xianpei, Han and
Zhiyuan, Liu and
Yulan, He",
booktitle = "Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)",
month = jul,
year = "2024",
address = "Taiyuan, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2024.ccl-1.5/",
pages = "57--70",
language = "zho",
abstract = "``该文研究基于HowNet的知识库描述语言语法体系的术语DEF自动生成问题,提出基于最近邻提示表征的术语DEF生成模型(NNP-TDGM),将训练集中的术语DEF构造为外显记忆集,在解码器生成(首)义原或关系时,检索与待预测术语概念结构相同或相近的术语所蕴含的核心概念,重要属性和关系类型,辅助模型完成DEF的生成,解决解码器在低频样本上训练不充分的问题。另外,通过提示预训练语言模型获得术语及术语定义内蕴涵概念信息的语义表征向量,改善编码器表征能力不足的问题。经实验验证NNP-TDGM模型生成术语DEF的义原-关系-义原三元组F1值达到31.84{\%}、关系F1值达到53.12{\%}、义原F1值达到51.55{\%}、首义原F1值达到68.53{\%},相对于基线方法分别提升了3.38{\%},1.45{\%},1.08{\%},0.48{\%}。''"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sijia-etal-2024-nnp">
<titleInfo>
<title>NNP-TDGM: 基于最近邻提示表征的术语DEF生成模型(NNP-TDGM: Nearest Neighbor Prompt Term DEF Generation Model)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sijia</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peiyan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shengren</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Libang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">zho</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sun</namePart>
<namePart type="family">Maosong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">Jiye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Han</namePart>
<namePart type="family">Xianpei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liu</namePart>
<namePart type="family">Zhiyuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">He</namePart>
<namePart type="family">Yulan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Taiyuan, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>“该文研究基于HowNet的知识库描述语言语法体系的术语DEF自动生成问题,提出基于最近邻提示表征的术语DEF生成模型(NNP-TDGM),将训练集中的术语DEF构造为外显记忆集,在解码器生成(首)义原或关系时,检索与待预测术语概念结构相同或相近的术语所蕴含的核心概念,重要属性和关系类型,辅助模型完成DEF的生成,解决解码器在低频样本上训练不充分的问题。另外,通过提示预训练语言模型获得术语及术语定义内蕴涵概念信息的语义表征向量,改善编码器表征能力不足的问题。经实验验证NNP-TDGM模型生成术语DEF的义原-关系-义原三元组F1值达到31.84%、关系F1值达到53.12%、义原F1值达到51.55%、首义原F1值达到68.53%,相对于基线方法分别提升了3.38%,1.45%,1.08%,0.48%。”</abstract>
<identifier type="citekey">sijia-etal-2024-nnp</identifier>
<location>
<url>https://aclanthology.org/2024.ccl-1.5/</url>
</location>
<part>
<date>2024-07</date>
<extent unit="page">
<start>57</start>
<end>70</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NNP-TDGM: 基于最近邻提示表征的术语DEF生成模型(NNP-TDGM: Nearest Neighbor Prompt Term DEF Generation Model)
%A Shen, Sijia
%A Wang, Peiyan
%A Wang, Shengren
%A Wang, Libang
%Y Maosong, Sun
%Y Jiye, Liang
%Y Xianpei, Han
%Y Zhiyuan, Liu
%Y Yulan, He
%S Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)
%D 2024
%8 July
%I Chinese Information Processing Society of China
%C Taiyuan, China
%G zho
%F sijia-etal-2024-nnp
%X “该文研究基于HowNet的知识库描述语言语法体系的术语DEF自动生成问题,提出基于最近邻提示表征的术语DEF生成模型(NNP-TDGM),将训练集中的术语DEF构造为外显记忆集,在解码器生成(首)义原或关系时,检索与待预测术语概念结构相同或相近的术语所蕴含的核心概念,重要属性和关系类型,辅助模型完成DEF的生成,解决解码器在低频样本上训练不充分的问题。另外,通过提示预训练语言模型获得术语及术语定义内蕴涵概念信息的语义表征向量,改善编码器表征能力不足的问题。经实验验证NNP-TDGM模型生成术语DEF的义原-关系-义原三元组F1值达到31.84%、关系F1值达到53.12%、义原F1值达到51.55%、首义原F1值达到68.53%,相对于基线方法分别提升了3.38%,1.45%,1.08%,0.48%。”
%U https://aclanthology.org/2024.ccl-1.5/
%P 57-70
Markdown (Informal)
[NNP-TDGM: 基于最近邻提示表征的术语DEF生成模型(NNP-TDGM: Nearest Neighbor Prompt Term DEF Generation Model)](https://aclanthology.org/2024.ccl-1.5/) (Shen et al., CCL 2024)
ACL