Papers by Richika Sharan

1 papers
What Should I Ask? Using Conversationally Informative Rewards for Goal-oriented Visual Dialog. (P19-1)

Copied to clipboard

Challenge: a new study challenges the ability of artificial agents to engage in goal-oriented conversations . goal-orientated visual dialogue is a challenging task since it requires a strategy and contextual information to achieve a goal.
Approach: They propose a goal-oriented visual dialogue system that combines reinforcement learning with regularized information gain.
Outcome: The proposed system outperforms current state-of-the-art models on the GuessWhat?! dataset.

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