Papers by Mohit Agrawal

1 papers
A Hierarchical VAE for Calibrating Attributes while Generating Text using Normalizing Flow (2021.acl-long)

Copied to clipboard

Challenge: Existing text-style transfer techniques focus on flipping the style attribute polarity instead of fine-grained regulation of attributes to generate multiple variants of a sentence.
Approach: They propose a hierarchical architecture for finer control over the attribute, preserving content using attribute dis- entanglement.
Outcome: The proposed framework generates natural looking sentences with finer control of intensity of a given attribute.

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