Evaluating the Values of Sources in Transfer Learning
Evaluating the Values of Sources in Transfer Learning
复制标题
DOI：
10.18653/v1/2021.naacl-main.402
复制
发表时间：
2021-04
期刊：
影响因子：
--
通讯作者：
Md. Rizwan Parvez;Kai-Wei Chang
中科院分区：
文献类型：
--
作者：
Md. Rizwan Parvez;Kai-Wei Chang
迁移学习将在数据丰富的源上训练的模型适应于低资源目标，已广泛应用于自然语言处理（NLP）。然而，当在多个源上训练传输模型时，并非每个源对目标都同样有用。为了更好地传输模型，了解源的值至关重要。在本文中，我们开发了一个有效的资源评估框架，用于量化资源的有用性（例如，）在基于Shapley值方法的迁移学习中的应用。对跨领域和跨语言迁移的实验和综合分析表明，该框架不仅能有效地选择有用的迁移源，而且源值与直观的源目标相似度相匹配。
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 , an efficient source valuation framework for quantifying the usefulness of the sources (e.g., ) in transfer learning based on the Shapley value method. Experiments and comprehensive analyses 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.