Merging Statistical Feature via Adaptive Gate for Improved Text Classification

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review

14 Scopus Citations
View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationThe Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21)
Place of PublicationPalo Alto, California
PublisherAAAI Press
Pages13288-13296
Number of pages9
ISBN (Print)978-1-57735-866-4 (set)
Publication statusPublished - 2021

Publication series

NameProceedings of the AAAI Conference on Artificial Intelligence
Number15
Volume35
ISSN (Print)2159-5399
ISSN (Electronic)2374-3468

Conference

Title35th AAAI Conference on Artificial Intelligence (AAAI-21)
LocationVirtual
Period2 - 9 February 2021

Abstract

Currently, text classification studies mainly focus on training classifiers by using textual input only, or enhancing semantic features by introducing external knowledge (e.g., hand-craft lexicons and domain knowledge). In contrast, some intrinsic statistical features of the corpus, like word frequency and distribution over labels, are not well exploited. Compared with external knowledge, the statistical features are deterministic and naturally compatible with corresponding tasks. In this paper, we propose an Adaptive Gate Network (AGN) to consolidate semantic representation with statistical features selectively. In particular, AGN encodes statistical features through a variational component and merges information via a well-designed valve mechanism. The valve adapts the information flow into the classifier according to the confidence of semantic features in decision making, which can facilitate training a robust classifier and can address the overfitting caused by using statistical features. Extensive experiments on datasets of various scales show that, by incorporating statistical information, AGN can improve the classification performance of CNN, RNN, Transformer, and Bert based models effectively. The experiments also indicate the robustness of AGN against adversarial attacks of manipulating statistical information.

Citation Format(s)

Merging Statistical Feature via Adaptive Gate for Improved Text Classification. / Li, Xianming; Li, Zongxi; XIE, Haoran et al.

The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21). Palo Alto, California : AAAI Press, 2021. p. 13288-13296 (Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 35, No. 15).

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review