Recent progress in leveraging deep learning methods for question answering

Tianyong Hao, Xinxin Li, Yulan He, Fu Lee Wang, Yingying Qu

Research output: Contribution to journalReview articlepeer-review

37 Citations (Scopus)

Abstract

Question answering, serving as one of important tasks in natural language processing, enables machines to understand questions in natural language and answer the questions concisely. From web search to expert systems, question answering systems are widely applied to various domains in assisting information seeking. Deep learning methods have boosted various tasks of question answering and have demonstrated dramatic effects in performance improvement for essential steps of question answering. Thus, leveraging deep learning methods for question answering has drawn much attention from both academia and industry in recent years. This paper provides a systematic review of the recent development of deep learning methods for question answering. The survey covers the scope including methods, datasets, and applications. The methods are discussed in terms of network structure characteristics, methodology innovations, and their effectiveness. The survey is expected to be a contribution to the summarization of recent research progress and future directions of deep learning methods for question answering.

Original languageEnglish
Pages (from-to)2765-2783
Number of pages19
JournalNeural Computing and Applications
Volume34
Issue number4
DOIs
Publication statusPublished - Feb 2022

Keywords

  • Dataset
  • Deep learning
  • Methods
  • Performance evaluation
  • Question answering

Fingerprint

Dive into the research topics of 'Recent progress in leveraging deep learning methods for question answering'. Together they form a unique fingerprint.

Cite this