Abstract
In low-resource settings, model transfer can help to overcome a lack of labeled data for many tasks and domains. However, predicting useful transfer sources is a challenging problem, as even the most similar sources might lead to unexpected negative transfer results. Thus, ranking methods based on task and text similarity — as suggested in prior work — may not be sufficient to identify promising sources. To tackle this problem, we propose a new approach to automatically determine which and how many sources should be exploited. For this, we study the effects of model transfer on sequence labeling across various domains and tasks and show that our methods based on model similarity and support vector machines are able to predict promising sources, resulting in performance increases of up to 24 F1 points.- Anthology ID:
- 2021.emnlp-main.689
- Volume:
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2021
- Address:
- Online and Punta Cana, Dominican Republic
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 8744–8753
- Language:
- URL:
- https://aclanthology.org/2021.emnlp-main.689
- DOI:
- 10.18653/v1/2021.emnlp-main.689
- Cite (ACL):
- Lukas Lange, Jannik Strötgen, Heike Adel, and Dietrich Klakow. 2021. To Share or not to Share: Predicting Sets of Sources for Model Transfer Learning. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 8744–8753, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- To Share or not to Share: Predicting Sets of Sources for Model Transfer Learning (Lange et al., EMNLP 2021)
- PDF:
- https://preview.aclanthology.org/nodalida-main-page/2021.emnlp-main.689.pdf
- Code
- boschresearch/predicting_sets_of_sources