TY - GEN
T1 - Evaluating the Values of Sources in Transfer Learning
AU - Parvez, Md Rizwan
AU - Chang, Kai Wei
N1 - Publisher Copyright:
© 2021 Association for Computational Linguistics.
PY - 2021
Y1 - 2021
N2 - Transfer learning that adapts a model trained on data-rich sources to low-resource targets has been widely applied in natural language processing (NLP). However, when training a transfer model over multiple sources, not every source is equally useful for the target. To better transfer a model, it is essential to understand the values of the sources. In this paper, we develop SEAL-Shap, an efficient source valuation framework for quantifying the usefulness of the sources (e.g., domains/languages) in transfer learning based on the Shapley value method. Experiments and comprehensive anal-yses on both cross-domain and cross-lingual transfers demonstrate that our framework is not only effective in choosing useful transfer sources but also the source values match the intuitive source-target similarity.
AB - Transfer learning that adapts a model trained on data-rich sources to low-resource targets has been widely applied in natural language processing (NLP). However, when training a transfer model over multiple sources, not every source is equally useful for the target. To better transfer a model, it is essential to understand the values of the sources. In this paper, we develop SEAL-Shap, an efficient source valuation framework for quantifying the usefulness of the sources (e.g., domains/languages) in transfer learning based on the Shapley value method. Experiments and comprehensive anal-yses on both cross-domain and cross-lingual transfers demonstrate that our framework is not only effective in choosing useful transfer sources but also the source values match the intuitive source-target similarity.
UR - https://www.scopus.com/pages/publications/85119648196
U2 - 10.18653/v1/2021.naacl-main.402
DO - 10.18653/v1/2021.naacl-main.402
M3 - Conference contribution
AN - SCOPUS:85119648196
T3 - NAACL-HLT 2021 - 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference
SP - 5084
EP - 5116
BT - NAACL-HLT 2021 - 2021 Conference of the North American Chapter of the Association for Computational Linguistics
PB - Association for Computational Linguistics (ACL)
T2 - 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2021
Y2 - 6 June 2021 through 11 June 2021
ER -