Papers by Daniel Gillblad

1 papers
Streaming word similarity mining on the cheap (D18-1)

Copied to clipboard

Challenge: Existing methods to estimate word similarities are to embed words in vector space and then calculate similarities between corresponding vectors.
Approach: They propose a method that explicitly counts second-order co-occurrences to estimate word similarities from streams.
Outcome: The proposed method is scalable, converges rapidly, behaves robustly under parameter changes, and captures word similarities on par with state-of-the-art word embeddings.

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