[Objective] This paper aims to improve the smart consulting systems to effectively answer academic questions. [Methods] We utilized deep learning, machine reading comprehension, data augmentation, information retrieval, and semantic similarity techniques to construct datasets and an academic knowledge question-answering system. Additionally, we designed a multi-paragraph recall metric to address the characteristics of academic literature and enhance retrieval accuracy with multidimensional features. [Results] Our new model’s ROUGE-L score reached 0.7338, with a question-answering accuracy of 88.65% and a multi-paragraph recall metric accuracy of 88.38%. [Limitations] We only examined the new model with single-domain content, which may limit the system’s performance in dealing with complex issues involving multiple domains. [Conclusions] The deep integration of machine reading comprehension technology with reference services can enhance the efficiency and sharing of academic resources and provide more comprehensive and accurate information support for researchers.
王翼虎, 白海燕. 基于机器阅读理解的智能咨询问答系统构建*[J]. 数据分析与知识发现, 2024, 8(5): 151-162.
Wang Yihu, Bai Haiyan. Constructing Smart Consulting Q&A System Based on Machine Reading Comprehension. Data Analysis and Knowledge Discovery, 2024, 8(5): 151-162.
(Zhou Taibing, Liu Wenyun. Comparative Analysis of Digital Reference Service in Public Libraries in China[J]. Information Studies: Theory & Application, 2010, 33(12): 84-87.)
(Liu Ze, Shao Bo, Wang Yi. Research on a Data-Driven Model for Smart Reference Service in Libraries[J]. Information Studies: Theory & Application, 2023, 46(5): 176-184.)
(Liu Qinghua, Tan Hongying. The Reference Service Patterns of Foreign Libraries[J]. Information Science, 2002, 20(6): 590-594.)
[4]
Liu S S, Zhang X, Zhang S, et al. Neural Machine Reading Comprehension: Methods and Trends[J]. Applied Sciences, 2019, 9(18): Article No.3698.
[5]
Qiu B Y, Chen X, Xu J G, et al. A Survey on Neural Machine Reading Comprehension[OL]. arXiv Preprint, arXiv: 1906.03824.
[6]
Li P, Li W, He Z Y, et al. Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering[OL]. arXiv Preprint, arXiv: 1607.06275.
[7]
Cui Y M, Liu T, Che W X, et al. A Span-Extraction Dataset for Chinese Machine Reading Comprehension[OL]. arXiv Preprint, arXiv: 1810.07366.
(Epidemic Government Q&A Assistant[EB/OL]. [2023-05-25]. https://www.datafountain.cn/competitions/424/datasets.)
[11]
Seo M, Kembhavi A, Farhadi A, et al. Bidirectional Attention Flow for Machine Comprehension[OL]. arXiv Preprint, arXiv: 1611.01603.
[12]
Yu A W, Dohan D, Luong M T, et al. QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension[OL]. arXiv Preprint, arXiv: 1804.09541.
[13]
Devlin J, Chang M W, Lee K, et al. BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding[OL]. arXiv Preprint, arXiv: 1810.04805.
[14]
Liu Y H, Ott M, Goyal N, et al. RoBERTa: A Robustly Optimized BERT Pretraining Approach[OL]. arXiv Preprint, arXiv: 1907.11692.
[15]
Lan Z Z, Chen M D, Goodman S, et al. ALBERT: A Lite BERT for Self-Supervised Learning of Language Representations[OL]. arXiv Preprint, arXiv: 1909.11942.
[16]
Cui Y M, Che W X, Liu T, et al. Revisiting Pre-Trained Models for Chinese Natural Language Processing[OL]. arXiv Preprint, arXiv: 2004.13922.
[17]
Brown T B, Mann B, Ryder N, et al. Language Models are Few-Shot Learners[C]// Proceedings of the 34th International Conference on Neural Information Processing Systems. ACM, 2020: 1877-1901.
[18]
Wang S H, Sun Y, Xiang Y, et al. ERNIE 3.0 Titan: Exploring Larger-Scale Knowledge Enhanced Pre-Training for Language Understanding and Generation[OL]. arXiv Preprint, arXiv: 2112.12731.
[19]
Zeng W, Ren X Z, Su T, et al. PanGu-α: Large-Scale Autoregressive Pretrained Chinese Language Models with Auto-Parallel Computation[OL]. arXiv Preprint, arXiv: 2104.12369.
[20]
Touvron H, Lavril T, Izacard G, et al. LLaMA: Open and Efficient Foundation Language Models[OL]. arXiv Preprint, arXiv: 2302.13971.
(Zhang Huaping, Li Linhan, Li Chunjin. ChatGPT Performance Evaluation on Chinese Language and Risk Measures[J]. Data Analysis and Knowledge Discovery, 2023, 7(3): 16-25.)
[22]
McNeal M, Newyear D. Chatbots: Automating Reference in Public Libraries[M]// Iglesias E. Robots in Academic Libraries:Advancements in Library Automation. Pennsylvania: IGI Global, 2013: 101-114.
[23]
Allison D. Chatbots in the Library: Is It Time?[J]. Library Hi Tech, 2012, 30(1): 95-107.
(Gu Denan. A Discussion on the Digital Reference Services of the National Science and Technology Library[J]. Library and Information Service, 2004, 48(1): 19-22.)
(Yao Fei, Zhang Chengyu, Chen Wu. The Mobile Application of ‘Xiaotu’—The Smart Talking Robot of Tsinghua University Library[J]. New Technology of Library and Information Service, 2014(7/8):120-126.)
(Sun Yi, Li Bao, Qu Jianfeng. Design and Implementation of Library Intelligent IM Reference Robot[J]. New Technology of Library and Information Service, 2011(5): 88-92.)
[27]
McKie I A S, Narayan B. Enhancing the Academic Library Experience with Chatbots: An Exploration of Research and Implications for Practice[J]. Journal of the Australian Library and Information Association, 2019, 68(3): 268-277.
(Wang Yi, Luo Jun. A Comparative Study on the Library Reference Knowledge Base Between China and U.S.A[J]. Library and Information Service, 2010, 54(17): 40-44.)
(Hu Xiaoge, Qi Yue, Wang Yuqi, et al. Design and Construction of Intelligent Question-Answer Knowledge Base for Library Reference and Consultancy[J]. Documentation, Information & Knowledge, 2019(5): 101-108.)
(Liu Ze, Xu Xiaojie, Shao Bo. Design and Application of Library Consultation Robot Based on Multi-Strategy Mixed Question Answering System Model[J]. New Century Library, 2022(5): 43-49.)
(Li Wenjiang, Chen Shiqin. Application of AIMLBot Intelligent Robot in Real-Time Virtual Reference Service[J]. New Technology of Library and Information Service, 2012(7/8):127-132.)
(Su Jianlin. Have Your Cake and Eat It: A SimBERT Model for Fusion Retrieval and Generation[EB/OL]. [2023-02-18]. https://kexue.fm/archives/7427.)
[33]
Bao H B, Dong L, Wei F R, et al. UNILMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training[C]// Proceedings of the 37th International Conference on Machine Learning. ACM, 2020: 642-652.
[34]
Luo R X, Xu J J, Zhang Y, et al. PKUSEG: A Toolkit for Multi-Domain Chinese Word Segmentation[OL]. arXiv Preprint, arXiv: 1906.11455.
[35]
Salton G, Buckley C. Term-Weighting Approaches in Automatic Text Retrieval[J]. Information Processing & Management, 1988, 24(5): 513-523.
[36]
Robertson S, Zaragoza H. The Probabilistic Relevance Framework: BM25 and Beyond[J]. Foundations and Trends in Information Retrieval, 2009, 3(4): 333-389.
[37]
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. ACM, 2017: 6000-6010.
[38]
Cui Y M, Che W X, Liu T, et al. Pre-Training with Whole Word Masking for Chinese BERT[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2021, 29: 3504-3514.
[39]
杨飞洪. 面向中文临床自然语言处理的BERT模型研究[D]. 北京: 北京协和医学院, 2021.
[39]
(Yang Feihong. Research on BERT Model for Chinese Clinical Language Processing[D]. Beijing: Peking Union Medical College, 2021.)
[40]
Lin C Y. Rouge: A Package for Automatic Evaluation of Summaries[M]// Text Summarization Branches Out. Association for Computational Linguistics, 2004: 74-81.