Weaver: Deep Co-Encoding of Questions and Documents for Machine Reading

Martin Raison
Martin Raison
Pierre-Emmanuel Mazaré
Pierre-Emmanuel Mazaré
Rajarshi Das
Rajarshi Das

arXiv: Computation and Language, Volume abs/1804.10490, 2018.

Cited by: 2|Bibtex|Views90
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

This paper aims at improving how machines can answer questions directly from text, with the focus of having models that can answer correctly multiple types of questions and from various types of texts, documents or even from large collections of them. To that end, we introduce the Weaver model that uses a new way to relate a question to a...More

Code:

Data:

Your rating :
0

 

Tags
Comments