The Library
Hierarchical interpretation of neural text classification
Tools
Tools
Tools
Yan, Hanqi, Gui, Lin and He, Yulan (2022) Hierarchical interpretation of neural text classification. Computational Linguistics, 48 (4). pp. 987-1020. doi:10.1162/coli_a_00459 ISSN 0891-2017.
![[img]](http://wrap.warwick.ac.uk/style/images/fileicons/application_pdf.png) |
PDF
WRAP-Hierarchical-interpretation-of-Neural-Text-Classification-Yan-2022.pdf - Accepted Version Embargoed item. Restricted access to Repository staff only - Requires a PDF viewer. Download (3505Kb) |
Official URL: https://doi.org/10.1162/coli_a_00459
Abstract
Recent years have witnessed increasing interests 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 paper 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.
| Item Type: | Journal Article | ||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Subjects: | Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software | ||||||||||||||||||
| Divisions: | Faculty of Science, Engineering and Medicine > Science > Computer Science | ||||||||||||||||||
| Library of Congress Subject Headings (LCSH): | Natural language processing (Computer science), Deep learning (Machine learning), Computer networks, Neural networks (Computer science) | ||||||||||||||||||
| Journal or Publication Title: | Computational Linguistics | ||||||||||||||||||
| Publisher: | MIT Press Direct | ||||||||||||||||||
| ISSN: | 0891-2017 | ||||||||||||||||||
| Official Date: | 1 December 2022 | ||||||||||||||||||
| Dates: |
|
||||||||||||||||||
| Volume: | 48 | ||||||||||||||||||
| Number: | 4 | ||||||||||||||||||
| Page Range: | pp. 987-1020 | ||||||||||||||||||
| DOI: | 10.1162/coli_a_00459 | ||||||||||||||||||
| Status: | Peer Reviewed | ||||||||||||||||||
| Publication Status: | Published | ||||||||||||||||||
| Access rights to Published version: | Open Access (Creative Commons) | ||||||||||||||||||
| Date of first compliant deposit: | 30 August 2022 | ||||||||||||||||||
| RIOXX Funder/Project Grant: |
|
||||||||||||||||||
| Open Access Version: |
Request changes or add full text files to a record
Repository staff actions (login required)
 |
View Item |
