Multi-Round Iterative Retrieval Algorithm for Parsing Question-Answering Process

被引：0

作者：

Changshun Z. ^{[1
,2
]}

Wenhao Y. ^{[2
]}

Shan Z. ^{[2
]}

Shengrong G. ^{[1
,2
]}

机构：

[1] School of Computer Science and Technology, Soochow University, Suzhou

[2] School of Computer Science and Engineering, Changshu Institute of Technology, Changshu

来源：

Data Analysis and Knowledge Discovery | 2024年 / 8卷 / 03期

基金：

美国国家科学基金会; 中国国家自然科学基金;

关键词：

Inference Sentence Retrieval; Multi-Round Iterations; Question-Answering Inference; Reading Comprehension Question-Answering; Unsupervised Framework;

D O I：

10.11925/infotech.2096-3467.2023.0092

中图分类号：

O212 [数理统计];

学科分类号：

摘要：

[Objective] This paper designs a retrieval model to explore the interpretability of question-answering tasks. It examines the reasoning processes of these reading comprehension models and improves sentence relevance in traditional unsupervised retrieval algorithms. [Methods] We proposed a new unsupervised retrieval model ISR, which integrated modules of Pearson correlation coefficient, GloVe word embeddings, and IDF weighting. The ISR model conducted fine-grained retrieval of inference sentences through multi-round iterations. [Results] The proposed model’s P, R, and F1 metrics were 2.4%, 1.8%, and 2.1% higher than the MSSwQ model on the MultiRC dataset. Its P, R, and F1 metrics were 4.8%, 2.6%, and 3.7% higher than the MSSwQ on the HotPotQA dataset. [Limitations] There might be excessive matching issues due to the model’s retrieval matching mechanism. [Conclusions] The proposed model improves the accuracy of retrieval inference sentences, which can be effectively applied to the question-answering tasks. © 2024 Chinese Academy of Sciences. All rights reserved.

引用

页码：120 / 131

页数：11

共 33 条

[1] Huang Xingyu, Design and Implementation of Medical Question Answering System Based on ALBERT, (2022)
[2] Fan Yihan, The Design and Implementation of Intelligent Question Answering System for Taxation, (2019)
[3] Huang Weiyi, Deep Neural Networks for Legal Question Answering Based on Knowledge Graph, (2020)
[4] Hu Yue, Zhou Guangyou, Question Generation from Knowledge Base with Graph Transformer, Journal of Chinese Information Processing, 36, 2, pp. 111-120, (2022)
[5] Gu Yingjie, Gui Xiaolin, Li Defu, Et al., Survey of Machine Reading Comprehension Based on Neural Network, Journal of Software, 31, 7, pp. 2095-2126, (2020)
[6] Wang Baocheng, Liu Lijun, Huang Qingsong, Retrieval of Similar Questions from Chinese Medical Question Answering Website, Journal of Chinese Information Processing, 36, 6, pp. 135-145, (2022)
[7] Zhao Yun, Liu Dexi, Wan Changxuan, Et al., Retrieval-Based Automatic Question Answer: A Literature Survey, Chinese Journal of Computers, 44, 6, pp. 1214-1232, (2021)
[8] Yang Shanshan, Jiang Lifen, Sun Huazhi, Et al., Multiple Choice Machine Reading Comprehension Based on Temporal Convolutional Network, Computer Engineering, 46, 11, pp. 97-103, (2020)
[9] Yang Z L, Qi P, Zhang S Z, Et al., HotpotQA: A Dataset for Diverse, Explainable Multi-Hop Question Answering, Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 2369-2380, (2018)
[10] Reddy S, Chen D Q, Manning C D., CoQA: A Conversational Question Answering Challenge, Proceedings of the Transactions of the Association for Computational Linguistics, pp. 249-266, (2019)

← 1 2 3 4 →