Making Neural QA as Simple as Possible but not Simpler

CONLL 2017 Dirk WeissenbornGeorg WieseLaura Seiffe

Recent development of large-scale question answering (QA) datasets triggered a substantial amount of research into end-to-end neural architectures for QA. Increasingly complex systems have been conceived without comparison to simpler neural baseline systems that would justify their complexity... (read more)

PDF Abstract CONLL 2017 PDF CONLL 2017 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Question Answering NewsQA FastQAExt F1 56.1 # 5
EM 43.7 # 4
Question Answering SQuAD1.1 FastQAExt EM 70.849 # 132
F1 78.857 # 138
Question Answering SQuAD1.1 FastQA EM 68.436 # 141
F1 77.070 # 150
Question Answering SQuAD1.1 dev FastQAExt (beam-size 5) EM 70.3 # 26
F1 78.5 # 30

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet