Papers by Jiwei Ding

1 papers
Leveraging Frequent Query Substructures to Generate Formal Queries for Complex Question Answering (D19-1)

Copied to clipboard

Challenge: Existing approaches build universal paraphrasing or ranking models for whole questions . current approaches build a universal ranking model for the whole questions, which fails for complex, long-tail questions.
Approach: They propose a new query generation approach based on frequent query substructures which helps rank existing query structures or build new query structures.
Outcome: The proposed approach significantly outperforms existing models on two benchmark datasets.

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