Abstract
Meta-Learning has emerged as a research direction to better transfer knowledge from related tasks to unseen but related tasks. However, Meta-Learning requires many training tasks to learn representations that transfer well to unseen tasks; otherwise, it leads to overfitting, and the performance degenerates to worse than Multi-task Learning. We show that a state-of-the-art data augmentation method worsens this problem of overfitting when the task diversity is low. We propose a simple method, TaskMix, which synthesizes new tasks by linearly interpolating existing tasks. We compare TaskMix against many baselines on an in-house multilingual intent classification dataset of N-Best ASR hypotheses derived from real-life human-machine telephony utterances and two datasets derived from MTOP. We show that TaskMix outperforms baselines, alleviates overfitting when task diversity is low, and does not degrade performance even when it is high.- Anthology ID:
- 2022.findings-aacl.6
- Volume:
- Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022
- Month:
- November
- Year:
- 2022
- Address:
- Online only
- Editors:
- Yulan He, Heng Ji, Sujian Li, Yang Liu, Chua-Hui Chang
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 67–72
- Language:
- URL:
- https://aclanthology.org/2022.findings-aacl.6
- DOI:
- Cite (ACL):
- Surya Kant Sahu. 2022. TaskMix: Data Augmentation for Meta-Learning of Spoken Intent Understanding. In Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022, pages 67–72, Online only. Association for Computational Linguistics.
- Cite (Informal):
- TaskMix: Data Augmentation for Meta-Learning of Spoken Intent Understanding (Sahu, Findings 2022)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2022.findings-aacl.6.pdf