Papers with fine-grained sentence-level divergences

1 papers
Detecting Fine-Grained Cross-Lingual Semantic Divergences without Supervision by Learning to Rank (2020.emnlp-main)

Copied to clipboard

Challenge: Detecting fine-grained differences in content conveyed in different languages is expensive and hard to scale.
Approach: They propose a training strategy for multilingual BERT models by learning to rank divergent examples of varying granularity.
Outcome: The proposed model improves the prediction and annotation of fine-grained semantic divergences.

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