Efficient Nearest Neighbor Emotion Classification with BERT-whitening

Wenbiao Yin, Lin Shang


Abstract
Retrieval-based methods have been proven effective in many NLP tasks. Previous methods use representations from the pre-trained model for similarity search directly. However, the sentence representations from the pre-trained model like BERT perform poorly in retrieving semantically similar sentences, resulting in poor performance of the retrieval-based methods. In this paper, we propose kNN-EC, a simple and efficient non-parametric emotion classification (EC) method using nearest neighbor retrieval. We use BERT-whitening to get better sentence semantics, ensuring that nearest neighbor retrieval works. Meanwhile, BERT-whitening can also reduce memory storage of datastore and accelerate retrieval speed, solving the efficiency problem of the previous methods. kNN-EC average improves the pre-trained model by 1.17 F1-macro on two emotion classification datasets.
Anthology ID:
2022.emnlp-main.312
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4738–4745
Language:
URL:
https://aclanthology.org/2022.emnlp-main.312
DOI:
10.18653/v1/2022.emnlp-main.312
Bibkey:
Cite (ACL):
Wenbiao Yin and Lin Shang. 2022. Efficient Nearest Neighbor Emotion Classification with BERT-whitening. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 4738–4745, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Efficient Nearest Neighbor Emotion Classification with BERT-whitening (Yin & Shang, EMNLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/2022.emnlp-main.312.pdf