Abstract
Fine-tuning the entire set of parameters of a large pretrained model has become the mainstream approach for transfer learning. To increase its efficiency and prevent catastrophic forgetting and interference, techniques like adapters and sparse fine-tuning have been developed. Adapters are modular, as they can be combined to adapt a model towards different facets of knowledge (e.g., dedicated language and/or task adapters). Sparse fine-tuning is expressive, as it controls the behavior of all model components. In this work, we introduce a new fine-tuning method with both these desirable properties. In particular, we learn sparse, real-valued masks based on a simple variant of the Lottery Ticket Hypothesis. Task-specific masks are obtained from annotated data in a source language, and language-specific masks from masked language modeling in a target language. Both these masks can then be composed with the pretrained model. Unlike adapter-based fine-tuning, this method neither increases the number of parameters at inference time nor alters the original model architecture. Most importantly, it outperforms adapters in zero-shot cross-lingual transfer by a large margin in a series of multilingual benchmarks, including Universal Dependencies, MasakhaNER, and AmericasNLI. Based on an in-depth analysis, we additionally find that sparsity is crucial to prevent both 1) interference between the fine-tunings to be composed and 2) overfitting. We release the code and models at https://github.com/cambridgeltl/composable-sft.- Anthology ID:
- 2022.acl-long.125
- Volume:
- Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1778–1796
- Language:
- URL:
- https://aclanthology.org/2022.acl-long.125
- DOI:
- 10.18653/v1/2022.acl-long.125
- Cite (ACL):
- Alan Ansell, Edoardo Ponti, Anna Korhonen, and Ivan Vulić. 2022. Composable Sparse Fine-Tuning for Cross-Lingual Transfer. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1778–1796, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- Composable Sparse Fine-Tuning for Cross-Lingual Transfer (Ansell et al., ACL 2022)
- PDF:
- https://preview.aclanthology.org/nodalida-main-page/2022.acl-long.125.pdf
- Code
- cambridgeltl/composable-sft + additional community code
- Data
- CoNLL-2003, GLUE, MLQA, MasakhaNER, MultiNLI, SQuAD, XQuAD