Hierarchical Interpretation of Neural Text Classification

被引:4
作者
Yan, Hanqi [1 ]
Gui, Lin [2 ]
He, Yulan [2 ,3 ,4 ]
机构
[1] Univ Warwick, Dept Comp Sci, Coventry, England
[2] Kings Coll London, Dept Informat, London, England
[3] Univ Warwick, Coventry, England
[4] Alan Turing Inst, London, England
基金
英国工程与自然科学研究理事会; 英国科研创新办公室;
关键词
This work was funded by the UK Engineering and Physical Sciences Research Council (grant no. EP/T017112/1; EP/V048597/1; EP/X019063/1). Hanqi Yan receives the PhD scholarship funded jointly by the University of Warwick and the Chinese Scholarship Council. Yulan He is supported by a Turing AI Fellowship funded by the UK Research and Innovation (grant no. EP/V020579/1);
D O I
10.1162/coli_a_00459
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Recent years have witnessed increasing interest in developing interpretable models in Natural Language Processing (NLP). Most existing models aim at identifying input features such as words or phrases important for model predictions. Neural models developed in NLP, however, often compose word semantics in a hierarchical manner. As such, interpretation by words or phrases only cannot faithfully explain model decisions in text classification. This article proposes a novel Hierarchical Interpretable Neural Text classifier, called HINT, which can automatically generate explanations of model predictions in the form of label-associated topics in a hierarchical manner. Model interpretation is no longer at the word level, but built on topics as the basic semantic unit. Experimental results on both review datasets and news datasets show that our proposed approach achieves text classification results on par with existing state-of-the-art text classifiers, and generates interpretations more faithful to model predictions and better understood by humans than other interpretable neural text classifiers.(1)
引用
收藏
页码:987 / 1020
页数:34
相关论文
共 57 条
[1]  
Abdou M., 2020, P 58 ANN M ASS COMP, P7590
[2]  
Alvarez-Melis D, 2018, ADV NEUR IN, V31
[3]   SECTOR: A Neural Model for Coherent Topic Segmentation and Classification [J].
Arnold, Sebastian ;
Schneider, Rudolf ;
Cudre-Mauroux, Philippe ;
Ger, Felix A. ;
Loeser, Alexander .
TRANSACTIONS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, 2019, 7 :169-184
[4]  
Bang S, 2021, AAAI CONF ARTIF INTE, V35, P11396
[5]  
Bastings J, 2019, 57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019), P2963
[6]   Latent Dirichlet allocation [J].
Blei, DM ;
Ng, AY ;
Jordan, MI .
JOURNAL OF MACHINE LEARNING RESEARCH, 2003, 3 (4-5) :993-1022
[7]  
Brown TB, 2020, ADV NEUR IN, V33
[8]  
Card D, 2018, PROCEEDINGS OF THE 56TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL), VOL 1, P2031
[9]  
Chaney Allison., 2021, P INT AAAI C WEB SOC, V6, P419
[10]  
Chen HJ, 2020, PROCEEDINGS OF THE 2020 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP), P4236