Papers with universal probing tasks

1 papers
Empirical Linguistic Study of Sentence Embeddings (P19-1)

Copied to clipboard

Challenge: a new method of analysing sentence embeddings shows that linguistic information is retained in the vector representations of sentences.
Approach: They propose a method of analysing the content of sentence embeddings based on probing tasks and contrasting languages.
Outcome: The proposed method is based on probing tasks and classification datasets for two contrasting languages.

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