Papers with word-level generation

1 papers
Generating Long and Informative Reviews with Aspect-Aware Coarse-to-Fine Decoding (P19-1)

Copied to clipboard

Challenge: Existing methods for review generation lack topical and syntactic characteristics of natural languages.
Approach: They propose a review generation model that uses aspect semantics, syntactic sketch, and context information to generate a sentence and corresponding words.
Outcome: The proposed model can generate long and informative review text for users given a product and her/his rating on it.

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