[1]钟茂生,孙 磊,罗贤增,等.融入句法结构和摘要信息的文本蕴含识别模型[J].计算机技术与发展,2023,33(10):120-127.[doi:10. 3969 / j. issn. 1673-629X. 2023. 10. 019]
 ZHONG Mao-sheng,SUN Lei,LUO Xian-zeng,et al.A Recognizing Textual Entailment Model Incorporating Syntactic Structure and Summary Information[J].,2023,33(10):120-127.[doi:10. 3969 / j. issn. 1673-629X. 2023. 10. 019]
点击复制

融入句法结构和摘要信息的文本蕴含识别模型()
分享到:

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
33
期数:
2023年10期
页码:
120-127
栏目:
人工智能
出版日期:
2023-10-10

文章信息/Info

Title:
A Recognizing Textual Entailment Model Incorporating Syntactic Structure and Summary Information
文章编号:
1673-629X(2023)10-0120-08
作者:
钟茂生孙 磊罗贤增王明文
江西师范大学 计算机信息工程学院,江西 南昌 330200
Author(s):
ZHONG Mao-shengSUN LeiLUO Xian-zengWANG Ming-wen
School of Computer Information Engineering,Jiangxi Normal University,Nanchang 330200,China
关键词:
文本蕴含识别摘要信息抽取句法结构互注意力自注意力
Keywords:
recognizing textual entailmentabstract information extractionsyntactic structuremutual attentionself-attention
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2023. 10. 019
摘要:
文本蕴含识别旨在推断两个句子之间的语义关系,通常分为蕴含、矛盾和中立三种类别。 目前,大多数文本蕴含识别方法都是通过互注意力的方法,判定句子之间的语义关系,这种方法只能捕捉局部交互信息,弱化了全局交互信息。据此,提出了融入句法结构和摘要信息的文本蕴含识别模型,通过结合自注意力和互注意力机制的方式,从句子的全局和局部交互信息考虑,并融入句子的句法结构信息,从而更准确地推测句子之间的语义关系;收集和整理了公务员试题的部分选择题,之后,将该模型和文本蕴含识别的思想应用于这部分试题,在试题中,使用摘要信息抽取的方法,解决公务员试题中题目冗长和答案简短导致的长度不对称问题。 实验结果表明,该模型在公共数据集和公务员试题上的表现,超越了多个基准模型。
Abstract:
Recognizing textual entailment aims to infer the semantic relationship between two sentences, usually divided into threecategories of entailment, contradiction and neutral. At present, most recognizing textual entailment methods use mutual attention todetermine the semantic relationship between sentences. This method can?
only capture local interaction information and weaken the globalinteraction information. Accordingly,a recognizing textual entailment model that integrates syntactic structure and abstract information isproposed. By combining self-attention and mutual attention mechanisms,the global and local interactive information of sentences?
is considered,and the syntactic structure information of sentences is integrated, so as to accurately infer the semantic relationship betweensentences. We collect and sort out some multiple-choice questions of civil servant test questions,and then apply the model and the ideaof textual entailment recognition to these test questions.?
In the test questions,the method of abstract information extraction is used tosolve asymmetric length problems caused by long questions and short answers in civil service examination questions. Experimental resultsshow that the proposed model outperforms several benchmark models on public datasets and civil servant test questions.
更新日期/Last Update: 2023-10-10