Papers with LT strategy

2 papers
Language Tags Matter for Zero-Shot Neural Machine Translation (2021.findings-acl)

Copied to clipboard

Challenge: Existing studies on multilingual machine translation have ignored the importance of LTs.
Approach: They propose to use language tag (LT) strategies to indicate translation directions in MNMT to enhance consistency and alleviate off-target issues in zero-shot directions.
Outcome: The proposed model could translate between unsupervised languages and achieve a +8 BLEU score difference over other LT strategies in translation tasks.
World Class Language Technology - Developing a Language Technology Strategy for Danish (2020.lrec-1)

Copied to clipboard

Challenge: Danish government adopts ambitious strategy for LT and artificial intelligence . 35 million DKK will be spent over a period of 6 years to develop platform .
Approach: They describe the process behind the development of the language-related parts of the strategy . they describe how focus areas and recommendations for the LT strategy were established .
Outcome: The Danish government adopted a new, ambitious strategy for LT and AI in March 2019 . the focus areas and recommendations for the LT strategy were established based on user feedback .

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