Por Qué Não Utiliser Alla Språk? Mixed Training with Gradient Optimization in Few-Shot Cross-Lingual Transfer

Anonymous

Paper Link: https://openreview.net/forum?id=f_NN0l6DfQo

Paper Type: Long paper (up to eight pages of content + unlimited references and appendices)

Abstract: The current state-of-the-art for few-shot cross-lingual transfer learning first trains on abundant labeled data in the source language and then fine-tunes with a few examples on the target language, termed target-adapting. Though this has been demonstrated to work on a variety of tasks, in this paper we show some deficiencies of this approach and propose a one-step mixed training method that trains on both source and target data with stochastic gradient surgery, a novel gradient-level optimization. Unlike the previous studies that focus on one language at a time when target-adapting, we use one model to handle all target languages simultaneously to avoid excessively language-specific models. Moreover, we discuss the unreality of utilizing large target development sets for model selection in previous literature. We further show that our method is both development-free for target languages, and is also able to escape from overfitting issues. We conduct a large-scale experiment on 4 diverse NLP tasks across up to 48 languages. Our proposed method achieves state-of-the-art performance on all tasks and outperforms target-adapting by a large margin, especially for languages that are linguistically distant from the source language, e.g., 7.36% F1 absolute gain on average for the NER task, up to 17.60% on Punjabi.

Presentation Mode: This paper will be presented in person in Seattle

Copyright Consent Signature (type Name Or NA If Not Transferrable): Haoran Xu

Copyright Consent Name And Address: Johns Hopkins University, 3400 N. Charles St. Baltimore, MD 21218-2683