Papers with multi-way aligned corpus

1 papers
EAG: Extract and Generate Multi-way Aligned Corpus for Complete Multi-lingual Neural Machine Translation (2022.acl-long)

Copied to clipboard

Challenge: Existing approaches to build multi-way aligned corpus from bilingual data are limited by their scale.
Approach: They propose to build a multi-way aligned corpus from bilingual data using two steps to extract candidate alignes and generate the final alignets from the candidates.
Outcome: The proposed method improves on two publicly available datasets with +1.1 and +1.4 BLEU points.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations