融合歧义感知的检索式问答方法

蒲晓; 何睿; 王志文; 黄珊珊; 袁霖; 吴渝

doi:10.13568/j.cnki.651094.651316.2023.07.10.0001

您当前的位置：

首页 >

文章列表页 >

融合歧义感知的检索式问答方法

信息科学与技术·人工智能专题 | 更新时间：2026-01-21

- 融合歧义感知的检索式问答方法
- 融合歧义感知的检索式问答方法
- 新疆大学学报（自然科学版中英文） 2024年41卷第1期页码：27-36
- 作者机构：
  
  1. 重庆邮电大学网络空间安全与信息法学院
  2. 武昌首义学院马克思主义学院
- 作者简介：
- 基金信息：
  
  重庆市自然科学基金面上项目“融合弱监督歧义感知的跨模态图文检索方法研究”（CSTB2022NSCQ-MSX1342）;重庆市教育委员会科学技术研究项目“融合弱监督语义消歧的文本匹配方法研究”（KJQN202300619）
- DOI：10.13568/j.cnki.651094.651316.2023.07.10.0001
  中图分类号： TP391.1
- 纸质出版：2024
- 稿件说明：
移动端阅览
[1]蒲晓,何睿,王志文,等.融合歧义感知的检索式问答方法[J].新疆大学学报(自然科学版)(中英文),2024,41(01):27-36.
[1]蒲晓,何睿,王志文,等.融合歧义感知的检索式问答方法[J].新疆大学学报(自然科学版)(中英文),2024,41(01):27-36. DOI： 10.13568/j.cnki.651094.651316.2023.07.10.0001.

DOI：10.13568/j.cnki.651094.651316.2023.07.10.0001.

摘要

针对多义词在不同上下文中语义表达不一致的问题，提出了一个融合歧义感知的问答模型，即模型在问题-候选答案的语义匹配过程中，与外部知识源相结合，动态识别并检测出每个多义词在不同场景下的语义，并将检测到的语义信息进行特征编码后融合到语义匹配任务中，使模型能够更为准确地理解每个词的精准含义，从而做出更为精准的匹配判断．在歧义感知模型的设计上，采用基于Transformer的深度语义编码器，使其能够更加全方位地抓取到待分析歧义词以及知识源的深度语义特征，从而做出更加准确的语义消歧．在标准检索式问答数据集上（Wiki QA和TrecQA）的实验结果表明，所提出的歧义感知的问答方法能够有效融合到多个基线模型中，并捕捉到多义词在不同语境中的精准语义，使其在包含公开数据集上的问答性能MAP评估高于对应基线模型约1%，且该语义特征使得基于BERT的文本相似性匹配模型的性能优于当前先进的其它模型．

Abstract

To solve the problem of inconsistent semantic expression of polysemous words in different contexts

we propose a sense-aware question-answer model. During the semantic matching process of questions and candidate answers

the model integrates with external knowledge sources to dynamically identify and detect the semantics of each polysemous word in different scenarios. The detected semantic information is encoded as features and then integrated into the semantic matching task

enabling the model to capture the exact meaning of each word and achieve better matching performance. In the design of the ambiguity perception model

we adopt a deep semantic encoder based on the Transformer

which enables it to capture more comprehensive depth semantic features of the analyzed ambiguous words and knowledge sources

making more accurate semantic disambiguation. Experimental results on standard retrieval-based Q&A datasets(WikiQA and TrecQA) demonstrate that the proposed senseaware Q&A method can effectively be integrated into multiple baseline models

capturing the precise semantics of polysemous words in different contexts. This approach achieves a MAP evaluation performance improvement of approximately 1% compared to corresponding baselines on public datasets. Moreover

this semantic feature enables a BERT-based text matching approach to outperform other state-of-the-art models.

关键词

Keywords

references

LI F L,QIU M H,CHEN H Q,et al.Ali M e Assist:An intelligent assistant for creating an innovative e-commerce experience[C]//Proceedings of the 2017 ACM on Conference on Information and Knowledge Management.Singapore,Singapore.ACM,2017:2495-2498．

CUI L,HUANG S H,WEI F R,et al.Super Agent:A customer service chatbot for e-commerce websites[C]//Proceedings of ACL2017,System Demonstrations.Vancouver,Canada.Stroudsburg,PA,USA:Association for Computational Linguistics,2017:97-102．

SONG S Y,WANG C,PU X,et al.An enhanced convolutional inference model with distillation for retrieval-based QA[C]//International Conference on Database Systems for Advanced Applications.Cham:Springer,2021:511-515．

HAO T Y,LI X X,HE Y L,et al.Recent progress in leveraging deep learning methods for question answering[J].Neural Computing and Applications,2022,34(4):2765-2783．

VASWANI A,SHAZEER N,PARMAR N,et al.Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems.December 4-9,2017,Long Beach,California,USA.ACM,2017:6000-6010．

MEDSKER L,JAIN L C.Recurrent neural networks:Design and applications[M].New York:CRC Press,2001．

LI F F,LU Y H,MAO X L,et al.Multi-task deep learning model based on hierarchical relations of address elements for semantic address matching[J].Neural Computing and Applications,2022,34(11):8919-8931．

HADIWINOTO C,NG H T,GAN W C.Improved word sense disambiguation using pre-trained contextualized word representations[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP).Hong Kong,China.Stroudsburg,PA,USA:Association for Computational Linguistics,2019:5297-5306．

SINGH V P,KUMAR P.Word sense disambiguation for Punjabi language using deep learning techniques[J].Neural Computing and Applications,2020,32:2963-2973．

WANG Y L,WANG M,FUJITA H.Word sense disambiguation:A comprehensive knowledge exploitation framework[J].Knowledge-Based Systems,2020,190:105030．

CHEN R C,YULIANTI E,SANDERSON M,et al.On the benefit of incorporating external features in a neural architecture for answer sentence selection[C]//Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval.August 7-11,2017,Shinjuku,Tokyo,Japan.ACM,2017:1017-1020．

KUNDU S,NG H T.A question-focused multi-factor attention network for question answering[J].Proceedings of the AAAIConference on Artificial Intelligence,2018,32(1):5828-5835．

DU X Y,SHAO J R,CARDIE C.Learning to ask:Neural question generation for reading comprehension[C]//Proceedings of the55th Annual Meeting of the Association for Computational Linguistics (Volume 1:Long Papers).Vancouver,Canada.Stroudsburg,PA,USA:Association for Computational Linguistics,2017:1342-1352．

YAN R,SONG Y P,WU H.Learning to respond with deep neural networks for retrieval-based human-computer conversation system[C]//Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval.July 17-21,2016,Pisa,Italy.ACM,2016:55-64．

WU B W,WANG B X,XUE H.Ranking responses oriented to conversational relevance in chat-bots[C]//Proceedings of COLING2016,the 26th International Conference on Computational Linguistics.December 11-17,2016,Osaka,Japan.2016:652-662．

AGIRRE E,EDMONDS P.Word sense disambiguation:Algorithms and applications (Text,Speech and Language Technology)[M].Berlin:Springer,2007．

MILLER G A.Word Net:A lexical database for English[J].Communications of the ACM,1995,38(11):39-41．

BANERJEE S,PEDERSEN T.An adapted Lesk algorithm for word sense disambiguation using Word Net[M]//Computational Linguistics and Intelligent Text Processing.Berlin,Heidelberg:Springer Berlin Heidelberg,2002:136-145．

BASILE P,CAPUTO A,SEMERARO G.An enhanced Lesk word sense disambiguation algorithm through a distributional semantic model[J].COLING 2014-25th International Conference on Computational Linguistics,Proceedings of COLING2014:Technical Papers,2014:1591-1600．

MORO A,RAGANATO A,NAVIGLI R.Entity linking meets word sense disambiguation:A unified approach[J].Transactions of the Association for Computational Linguistics,2014,2:231-244．

HUANG L Y,SUN C,QIU X P,et al.Gloss BERT:BERT for word sense disambiguation with gloss knowledge[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP).Hong Kong,China.Stroudsburg,PA,USA:Association for Computational Linguistics,2019:3509-3514．

YAP B P,KOH A,CHNG E S.Adapting BERT for word sense disambiguation with gloss selection objective and example sentences[C]//Findings of the Association for Computational Linguistics:EMNLP 2020.Online.Stroudsburg,PA,USA:Association for Computational Linguistics,2020:41-46．

BIRD S.NLTK:The natural language toolkit[C]//Proceedings of the COLING/ACL on Interactive Presentation Sessions.ACM,2006:69-72．

YIN W P,SCH¨UTZE H,XIANG B,et al.ABCNN:Attention-based convolutional neural network for modeling sentence pairs[J].Transactions of the Association for Computational Linguistics,2016,4:259-272．

YANG R Q,ZHANG J H,GAO X,et al.Simple and effective text matching with richer alignment features[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.Florence,Italy.Stroudsburg,PA,USA:Association for Computational Linguistics,2019:4699-4709．

YANG Y,YIH W T,MEEK C.Wiki QA:A challenge dataset for open-domain question answering[C]//Proceedings of the 2015Conference on Empirical Methods in Natural Language Processing.Lisbon,Portugal.Stroudsburg,PA,USA:Association for Computational Linguistics,2015:2013-2018．

WANG M Q,SMITH N A,MITAMURA T.What is the Jeopardy model?A quasi-synchronous grammar for QA[C]//EMNLP-Co NLL 2007-Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning.June 28-30,2007,Prague,Czech Republic.Stroudsburg:ACL,2007:22-32．

LIU T,WANG X,LYU C G,et al.Sentence matching with syntax-and semantics-aware BERT[C]//Proceedings of the 28th International Conference on Computational Linguistics.Barcelona,Spain(Online).Stroudsburg,PA,USA:International Committee on Computational Linguistics,2020:3302-3312．

ZHANG Z S,WU Y W,ZHAO H,et al.Semantics-aware BERT for language understanding[J].Proceedings of the AAAIConference on Artificial Intelligence,2020,34(5):9628-9635.

浏览量

105

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据