A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task

ACL 2016 Danqi ChenJason BoltonChristopher D. Manning

Enabling a computer to understand a document so that it can answer comprehension questions is a central, yet unsolved goal of NLP. A key factor impeding its solution by machine learned systems is the limited availability of human-annotated data... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Question Answering CNN / Daily Mail Classifier CNN 67.9 # 14
Daily Mail 68.3 # 9
Question Answering CNN / Daily Mail Attentive + relabling + ensemble CNN 77.6 # 3
Daily Mail 79.2 # 3
Question Answering CNN / Daily Mail AttentiveReader + bilinear attention CNN 72.4 # 11
Daily Mail 75.8 # 6