Multilingual and cross-lingual document classification: A meta-learning approach

March 07, 2022


The great majority of languages in the world are considered under-resourced for successful application of deep learning methods. In this work, we propose a meta-learning approach to document classification in low-resource languages and demonstrate its effectiveness in two different settings: few-shot, cross-lingual adaptation to previously unseen languages; and multilingual joint-training when limited target-language data is available during training. We conduct a systematic comparison of several meta-learning methods, investigate multiple settings in terms of data availability, and show that meta-learning thrives in settings with a heterogeneous task distribution. We propose a simple, yet effective adjustment to existing meta-learning methods which allows for better and more stable learning, and set a new state-of-the-art on a number of languages while performing on-par on others, using only a small amount of labeled data.

Download the Paper


Written by

Pushkar Mishra

Ekaterina Shutova

Helen Yannakoudakis

Niels van der Heijden



Help Us Pioneer The Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.