Meta-Learning for Effective Multi-task and Multilingual Modelling
Abstract
Natural language processing (NLP) tasks (e.g. question-answering in English) benefit from knowledge of other tasks (e.g. named entity recognition in English) and knowledge of other languages (e.g. question-answering in Spanish). Such shared representations are typically learned in isolation, either across tasks or across languages. In this work, we propose a meta-learning approach to learn the interactions between both tasks and languages. We also investigate the role of different sampling strategies used during meta-learning. We present experiments on five different tasks and six different languages from the XTREME multilingual benchmark dataset. Our meta-learned model clearly improves in performance compared to competitive baseline models that also include multi-task baselines. We also present zero-shot evaluations on unseen target languages to demonstrate the utility of our proposed model.
Cite
@article{arxiv.2101.10368,
title = {Meta-Learning for Effective Multi-task and Multilingual Modelling},
author = {Ishan Tarunesh and Sushil Khyalia and Vishwajeet Kumar and Ganesh Ramakrishnan and Preethi Jyothi},
journal= {arXiv preprint arXiv:2101.10368},
year = {2021}
}
Comments
In Proceedings of The 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2021)