Robust Text Classifier on Test-Time Budgets

Md Rizwan Parvez, Tolga Bolukbasi, Kai-Wei Chang, Venkatesh Saligrama


Abstract
We design a generic framework for learning a robust text classification model that achieves high accuracy under different selection budgets (a.k.a selection rates) at test-time. We take a different approach from existing methods and learn to dynamically filter a large fraction of unimportant words by a low-complexity selector such that any high-complexity state-of-art classifier only needs to process a small fraction of text, relevant for the target task. To this end, we propose a data aggregation method to train the classifier, allowing it to achieve competitive performance on fractured sentences. On four benchmark text classification tasks, we demonstrate that the framework gains consistent speedup with little degradation in accuracy on various selection budgets.
Anthology ID:
D19-1108
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1167–1172
Language:
URL:
https://aclanthology.org/D19-1108
DOI:
10.18653/v1/D19-1108
Bibkey:
Cite (ACL):
Md Rizwan Parvez, Tolga Bolukbasi, Kai-Wei Chang, and Venkatesh Saligrama. 2019. Robust Text Classifier on Test-Time Budgets. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1167–1172, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Robust Text Classifier on Test-Time Budgets (Parvez et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1108.pdf
Attachment:
 D19-1108.Attachment.pdf
Code
 uclanlp/Fast-and-Robust-Text-Classification
Data
AG NewsIMDb Movie ReviewsSSTSST-2