CLLGDec 11, 2019

MetaMT,a MetaLearning Method Leveraging Multiple Domain Data for Low Resource Machine Translation

arXiv:1912.05467v143 citations
Originality Synthesis-oriented
AI Analysis

This addresses the challenge of limited training data for machine translation, but appears incremental as it builds on existing meta-learning and data manipulation techniques.

The paper tackles the problem of low-resource machine translation by leveraging multiple domain data through meta-learning, resulting in robust neural models.

Manipulating training data leads to robust neural models for MT.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes