2 papers
cs.CL2017
A Neural Comprehensive Ranker (NCR) for Open-Domain Question Answering
Bin Bi, Hao Ma
This paper proposes a novel neural machine reading model for open-domain question answering at scale. Existing machine comprehension models typically assume that a short piece of r…
cs.CL2017
KeyVec: Key-semantics Preserving Document Representations
Bin Bi, Hao Ma
Previous studies have demonstrated the empirical success of word embeddings in various applications. In this paper, we investigate the problem of learning distributed representatio…