Research on automatic detection of text-oriented counterfactual statements

Ke Wang; Yunze Wang; Tianzheng Wang; Kaihao Zhou; Fangming Gu

doi:10.1117/12.2642609

28 July 2022 Research on automatic detection of text-oriented counterfactual statements

Ke Wang, Yunze Wang, Tianzheng Wang, Kaihao Zhou, Fangming Gu

Proceedings Volume 12303, International Conference on Cloud Computing, Internet of Things, and Computer Applications (CICA 2022); 123032H (2022) https://doi.org/10.1117/12.2642609
Event: International Conference on Cloud Computing, Internet of Things, and Computer Applications, 2022, Luoyang, China

Abstract

Counter-fact is the highest form of causal reasoning. Focusing on counter-fact will provide new ideas for higher order causal reasoning. For counterfactual text detection, two detection methods are proposed. One is the automatic detection method based on classification model, that is, counterfactual detection is carried out on the given annotated text data. In this way, the data imbalance problem is solved first, then word vector is generated by doc2vec, and finally the binary SVM training model is adopted.The second is automatic detection method based on sequence annotation model, namely the counterfactual statements of reason and result orientation, to this sequence labeling method is adopted, the individual words in the text annotation, after processing the data to be included in the BiLSTM after training, and through a layer of conditions with the airport, the resulting text labeling information. Experiments show that the proposed method can accurately detect and locate the cause and result in the counterfactual text.

Citation Download Citation

Ke Wang, Yunze Wang, Tianzheng Wang, Kaihao Zhou, and Fangming Gu "Research on automatic detection of text-oriented counterfactual statements", Proc. SPIE 12303, International Conference on Cloud Computing, Internet of Things, and Computer Applications (CICA 2022), 123032H (28 July 2022); https://doi.org/10.1117/12.2642609

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available