Reading Wikipedia to Answer Open-Domain Questions

ACL 2017 Danqi ChenAdam FischJason WestonAntoine Bordes

This paper proposes to tackle open- domain question answering using Wikipedia as the unique knowledge source: the answer to any factoid question is a text span in a Wikipedia article. This task of machine reading at scale combines the challenges of document retrieval (finding the relevant articles) with that of machine comprehension of text (identifying the answer spans from those articles)... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Open-Domain Question Answering SQuAD1.1 DrQA EM 70 # 1
Question Answering SQuAD1.1 Document Reader (single model) EM 70.733 # 127
Question Answering SQuAD1.1 Document Reader (single model) F1 79.353 # 129
Question Answering SQuAD1.1 dev DrQA (Document Reader only) EM 69.5 # 26
Question Answering SQuAD1.1 dev DrQA (Document Reader only) F1 78.8 # 28