A Self-enhancement Multitask Framework for Unsupervised Aspect Category Detection

Thi-Nhung Nguyen, Hoang Ngo, Kiem-Hieu Nguyen, Tuan-Dung Cao


Abstract
Our work addresses the problem of unsupervised Aspect Category Detection using a small set of seed words. Recent works have focused on learning embedding spaces for seed words and sentences to establish similarities between sentences and aspects. However, aspect representations are limited by the quality of initial seed words, and model performances are compromised by noise. To mitigate this limitation, we propose a simple framework that automatically enhances the quality of initial seed words and selects high-quality sentences for training instead of using the entire dataset. Our main concepts are to add a number of seed words to the initial set and to treat the task of noise resolution as a task of augmenting data for a low-resource task. In addition, we jointly train Aspect Category Detection with Aspect Term Extraction and Aspect Term Polarity to further enhance performance. This approach facilitates shared representation learning, allowing Aspect Category Detection to benefit from the additional guidance offered by other tasks. Extensive experiments demonstrate that our framework surpasses strong baselines on standard datasets.
Anthology ID:
2023.emnlp-main.500
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8043–8054
Language:
URL:
https://aclanthology.org/2023.emnlp-main.500
DOI:
10.18653/v1/2023.emnlp-main.500
Bibkey:
Cite (ACL):
Thi-Nhung Nguyen, Hoang Ngo, Kiem-Hieu Nguyen, and Tuan-Dung Cao. 2023. A Self-enhancement Multitask Framework for Unsupervised Aspect Category Detection. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 8043–8054, Singapore. Association for Computational Linguistics.
Cite (Informal):
A Self-enhancement Multitask Framework for Unsupervised Aspect Category Detection (Nguyen et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.500.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.500.mp4