Discriminatively-Tuned Generative Classifiers for Robust Natural Language Inference

Xiaoan Ding, Tianyu Liu, Baobao Chang, Zhifang Sui, Kevin Gimpel


Abstract
While discriminative neural network classifiers are generally preferred, recent work has shown advantages of generative classifiers in term of data efficiency and robustness. In this paper, we focus on natural language inference (NLI). We propose GenNLI, a generative classifier for NLI tasks, and empirically characterize its performance by comparing it to five baselines, including discriminative models and large-scale pretrained language representation models like BERT. We explore training objectives for discriminative fine-tuning of our generative classifiers, showing improvements over log loss fine-tuning from prior work (Lewis and Fan, 2019). In particular, we find strong results with a simple unbounded modification to log loss, which we call the “infinilog loss”. Our experiments show that GenNLI outperforms both discriminative and pretrained baselines across several challenging NLI experimental settings, including small training sets, imbalanced label distributions, and label noise.
Anthology ID:
2020.emnlp-main.657
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8189–8202
Language:
URL:
https://aclanthology.org/2020.emnlp-main.657
DOI:
10.18653/v1/2020.emnlp-main.657
Bibkey:
Cite (ACL):
Xiaoan Ding, Tianyu Liu, Baobao Chang, Zhifang Sui, and Kevin Gimpel. 2020. Discriminatively-Tuned Generative Classifiers for Robust Natural Language Inference. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 8189–8202, Online. Association for Computational Linguistics.
Cite (Informal):
Discriminatively-Tuned Generative Classifiers for Robust Natural Language Inference (Ding et al., EMNLP 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2020.emnlp-main.657.pdf
Video:
 https://slideslive.com/38938994
Code
 tyliupku/gen-nli
Data
GLUEMultiNLISICKSNLI