Survey on Commonsense Question Answering

被引：0
|
作者：
Fan Y.-F. [1 ]
Zou B.-W. [2 ]
Xu Q.-T. [1 ]
Li Z.-F. [1 ]
Hong Y. [1 ]
机构：
[1] School of Computer Science & Technology, Soochow University, Suzhou
[2] Infocomm Research Institute of Singapore, Singapore
来源：
Hong, Yu (tianxianer@gmail.com) | 1600年 / Chinese Academy of Sciences卷 / 35期
关键词：
common sense knowledge source; common sense knowledge type; commonsense question answering;
D O I：
10.13328/j.cnki.jos.006913
中图分类号：
学科分类号：
摘要：
Commonsense question answering is an essential natural language understanding task that aims to solve natural language questions automatically by using commonsense knowledge to obtain accurate answers. It has a broad application prospect in areas such as virtual assistants or social chatbots and contains crucial scientific issues such as knowledge mining and representation, language understanding and computation, and answer reasoning and generation. Therefore, it has received wide attention from industry and academia. This study first introduces the main datasets in commonsense question answering. Secondly, it summarizes the distinctions between different sources of commonsense knowledge in terms of construction methods, knowledge sources, and presentation forms. Meanwhile, the study focuses on the analysis and comparison of the state-of-the-art commonsense question answering models, as well as the characteristic methods fusing commonsense knowledge. Particularly, based on the commonalities and characteristics of commonsense knowledge in different question answering task scenarios, this study establishes a commonsense knowledge classification system containing attribute, semantic, causal, context, abstract, and intention. On this basis, it conducts prospective research on the construction of commonsense knowledge datasets, the collaboration mechanism of perceptual knowledge fusion and pre-trained language models, and corresponding commonsense knowledge pre-classification techniques. Furthermore, the study reports specifically on the performance changes in the above models under cross-dataset migration scenarios and their potential contributions in commonsense answer reasoning. On the whole, this study gives a comprehensive review of existing data and state-of-the-art technologies, as well as a pre-research for the construction of cross-data knowledge systems, technology migration, and generalization, so as to provide references for the further development of theories and technologies while reporting on the existing technologies in the field. © 2024 Chinese Academy of Sciences. All rights reserved.
引用
收藏
页码：236 / 265
页数：29
相关论文
共 90 条
  • [1] Pujara J, Miao H, Getoor L, Cohen W., Knowledge graph identification, Proc. of the 12th Int’l Semantic Web Conf, pp. 542-557, (2013)
  • [2] Wang X, Zou L, Wang CK, Peng P, Feng ZY., Research on knowledge graph data management: A survey, Ruan Jian Xue Bao/Journal of Software, 30, 7, pp. 2139-2174, (2019)
  • [3] Holland PW., Statistics and causal inference, Journal of the American statistical Association, 81, 396, pp. 945-960, (1986)
  • [4] Settles B, Craven M., An analysis of active learning strategies for sequence labeling tasks, Proc. of the 2008 Conf. on Empirical Methods in Natural Language Processing, pp. 1070-1079, (2008)
  • [5] Liu H, Singh P., ConceptNet—A practical commonsense reasoning tool-kit, BT Technology Journal, 22, 4, pp. 211-226, (2004)
  • [6] Zaremba W, Sutskever I, Vinyals O., Recurrent neural network regularization, (2015)
  • [7] Hochreiter S, Schmidhuber J., Long short-term memory, Neural Computation, 9, 8, pp. 1735-1780, (1997)
  • [8] Bahdanau D, Cho K, Bengio Y., Neural machine translation by jointly learning to align and translate, Proc. of the 3rd Int’l Conf. on Learning Representations, pp. 1-15, (2015)
  • [9] Devlin J, Chang M W, Lee K, Toutanova K., BERT: Pre-training of deep bidirectional transformers for language understanding, Proc. of the 2019 Conf. of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Vol. 1 (Long and Short Papers), pp. 4171-4186, (2019)
  • [10] Liu Z, Lin W, Shi Y, Zhao J., A robustly optimized BERT pre-training approach with post-training, Proc. of the 20th Chinese National Conf. on Computational Linguistics, pp. 1218-1227, (2021)
123456789