Papers with unsupervised learning strategy

1 papers
Unsupervised Preference-Aware Language Identification (2022.findings-acl)

Copied to clipboard

Challenge: Existing studies do not consider inter-personal variations due to the lack of user annotated training data.
Approach: They propose to use user preferences to identify ambiguous texts in multilingual applications without user annotated training data to build a preference-aware LID model.
Outcome: The proposed model significantly outperforms existing LID systems on handling ambiguous texts.

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