Question Answering with Subgraph Embeddings
Antoine Bordes
and
Sumit Chopra
and
Jason Weston
arXiv e-Print archive - 2014 via Local arXiv
Keywords:
cs.CL
First published: 2014/06/14 (10 years ago) Abstract: This paper presents a system which learns to answer questions on a broad
range of topics from a knowledge base using few hand-crafted features. Our
model learns low-dimensional embeddings of words and knowledge base
constituents; these representations are used to score natural language
questions against candidate answers. Training our system using pairs of
questions and structured representations of their answers, and pairs of
question paraphrases, yields competitive results on a competitive benchmark of
the literature.
