Intelligent Question Answering in Restricted Domains Using Deep Learning and Question Pair Matching
| Autor: | Sitong Zhou, Min Wei, Linqin Cai, Xun Yan |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
General Computer Science
business.industry Computer science Semantic analysis (machine learning) Deep learning question pair matching General Engineering 020206 networking & telecommunications 02 engineering and technology Convolutional neural network Domain (software engineering) BiLSTM intelligent question answering 0202 electrical engineering electronic engineering information engineering Question answering Feature (machine learning) 020201 artificial intelligence & image processing General Materials Science The Internet Artificial intelligence lcsh:Electrical engineering. Electronics. Nuclear engineering business attention mechanism lcsh:TK1-9971 CNN |
| Zdroj: | IEEE Access, Vol 8, Pp 32922-32934 (2020) |
| ISSN: | 2169-3536 |
| Popis: | With the rapid expansion of the Internet, intelligent question answering for information retrieval has once again gained widespread attention. However, current question answering models mainly focus on the general and common-sense questions in open domains and are incapable to effectively solve more complex professional domain questions. This paper proposed an integrated framework for Chinese intelligent question answering in restricted domains. The proposed model fused convolutional neural network and bidirectional long short-term memory network which performs efficient semantic analysis on the question pairs to extract more effective features of the text. Meanwhile, the coattention mechanism and attention mechanism were combined to obtain the semantic interaction and feature representation of the question pair for providing complete information for subsequent calculations. In addition, we introduced the method of question pair matching to implement the Chinese intelligent question answering in a restricted domain. Experiments were tested and evaluated on the open-source CCKS2018 dataset and our private self-built inverted pendulum control question answering (IPC-QA) dataset for automation control virtual learning environment. Experimental results confirm that the proposed models are efficient and achieve a high precision of 0.86042 and 0.8031 on CCKS2018 and IPC-QA respectively. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|