Gated-Attention Readers for Text Comprehension

ACL 2017 Bhuwan DhingraHanxiao LiuZhilin YangWilliam W. CohenRuslan Salakhutdinov

In this paper we study the problem of answering cloze-style questions over documents. Our model, the Gated-Attention (GA) Reader, integrates a multi-hop architecture with a novel attention mechanism, which is based on multiplicative interactions between the query embedding and the intermediate states of a recurrent neural network document reader... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Question Answering Children's Book Test NSE Accuracy-CN 71.9% # 2
Accuracy-NE 73.2% # 3
Question Answering Children's Book Test GA + feature + fix L(w) Accuracy-CN 70.7% # 3
Accuracy-NE 74.9% # 2
Question Answering Children's Book Test GA reader Accuracy-CN 69.4% # 4
Accuracy-NE 71.9% # 5
Question Answering CNN / Daily Mail GA Reader CNN 77.9 # 2
Daily Mail 80.9 # 1
Open-Domain Question Answering Quasar GA EM (Quasar-T) 26.4 # 5
F1 (Quasar-T) 26.4 # 6