Meta-curriculum Learning For Domain Adaptation In Neural Machine Translation | Awesome LLM Papers Add your paper to Awesome LLM Papers

Meta-curriculum Learning For Domain Adaptation In Neural Machine Translation

Runzhe Zhan, Xuebo Liu, Derek F. Wong, Lidia S. Chao . Proceedings of the AAAI Conference on Artificial Intelligence 2021 – 42 citations

[Code] [Paper]   Search on Google Scholar   Search on Semantic Scholar
AAAI Compositional Generalization Fine Tuning Has Code Interdisciplinary Approaches Neural Machine Translation Security Training Techniques

Meta-learning has been sufficiently validated to be beneficial for low-resource neural machine translation (NMT). However, we find that meta-trained NMT fails to improve the translation performance of the domain unseen at the meta-training stage. In this paper, we aim to alleviate this issue by proposing a novel meta-curriculum learning for domain adaptation in NMT. During meta-training, the NMT first learns the similar curricula from each domain to avoid falling into a bad local optimum early, and finally learns the curricula of individualities to improve the model robustness for learning domain-specific knowledge. Experimental results on 10 different low-resource domains show that meta-curriculum learning can improve the translation performance of both familiar and unfamiliar domains. All the codes and data are freely available at https://github.com/NLP2CT/Meta-Curriculum.

Similar Work