What's Missing: A Knowledge Gap Guided Approach for Multi-hop Question Answering

EMNLP/IJCNLP (1), pp. 2814-2828, 2019.

Cited by: 7|Bibtex|Views28|DOI:https://doi.org/10.18653/v1/D19-1281
EI
Other Links: arxiv.org|dblp.uni-trier.de

Abstract:

Multi-hop textual question answering requires combining information from multiple sentences. We focus on a natural setting where, unlike typical reading comprehension, only partial information is provided with each question. The model must retrieve and use additional knowledge to correctly answer the question. To tackle this challenge, ...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments