Papers by Jean Charbonnier

1 papers
Using Word Embeddings for Unsupervised Acronym Disambiguation (C18-1)

Copied to clipboard

Challenge: Scientific papers contain many acronyms and abbreviations.
Approach: They propose a method to choose the contextual correct definition of an acronym . they learn word embeddings for all words in the corpus and compare them with weighted averages .
Outcome: The proposed method outperforms (classical) cosine similarity in a set of scientific papers.

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