模式识别与人工智能
Thursday, Apr. 3, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
  2020, Vol. 33 Issue (2): 106-112    DOI: 10.16451/j.cnki.issn1003-6059.202002002
Papers and Reports Current Issue| Next Issue| Archive| Adv Search |
Label-Enhanced Reading Comprehension Model
SU Lixin1,2, GUO Jiafeng1,2, FAN Yixing1, LAN Yanyan1,2, CHENG Xueqi3
1. Key Laboratory of Network Data Science and Technology, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190;
2. School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing 100190;
3. Institute of Network Technology, Institute of Computing Technology (YANTAI), Chinese Academy of Sciences, Yantai 264005

Download: PDF (771 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  In the existing extractive reading comprehension models, only the boundary of answers is utilized as the supervision signal and the labeling processed by human is ignored. Consequently, learned models are prone to learn the superficial features and the generalization performance is degraded. In this paper, a label-enhanced reading comprehension model is proposed to imitate human activity. The answer-bearing sentence, the content and the boundary of the answer are learned simultaneously. The answer-bearing sentence and the content of the answer can be derived from the boundary of the answer and these three types of labels are regarded as supervision signals. The model is trained by multitask learning. During prediction, the probabilities from three predictions are merged to determine the answer, and thus the generalization performance is improved. Experiments on SQuAD dataset demonstrate the effectiveness of LE-Reader model.
Key wordsReading Comprehension      Multitask Learning      Answer Extraction     
Received: 18 October 2019     
ZTFLH: TP 391  
Fund:Supported by National Key Research and Development Program of China(No.2016QY02D0405), National Natural Science Foundation of China(No.61425016,61722211,61773362,61872338,61902381), Youth Innovation Promotion Association of CAS(No.20144310,2016102), Foundation and Frontier Research Key Program of Chongqing Science and Technology Commission(No.cstc2017jcyjBX0059), Taishan Scholars Program of Shandong Province(No.ts201511082)
Corresponding Authors: GUO Jiafeng, Ph.D., professor. His research interests include data mining and information retrieval.   
About author:: SU Lixin, Ph.D. candidate. His research interests include information retrieval and question answering; FAN Yixing, Ph.D., research assistant. His research interests include data mining and information retrieval; LAN Yanyan, Ph.D., associate professor. Her research interests include machine lear-ning and data mining; CHENG Xueqi, Ph.D., professor. His research interests include network science and social computing, web search and data mi-ning.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
SU Lixin
GUO Jiafeng
FAN Yixing
LAN Yanyan
CHENG Xueqi
Cite this article:   
SU Lixin,GUO Jiafeng,FAN Yixing等. Label-Enhanced Reading Comprehension Model[J]. , 2020, 33(2): 106-112.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202002002      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2020/V33/I2/106
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn