FusionNet: Fusing via Fully-Aware Attention with Application to Machine Comprehension

This paper introduces a new neural structure called FusionNet, which extends existing attention approaches from three perspectives. First, it puts forward a novel concept of "history of word" to characterize attention information from the lowest word-level embedding up to the highest semantic-level representation... Second, it introduces an improved attention scoring function that better utilizes the "history of word" concept. Third, it proposes a fully-aware multi-level attention mechanism to capture the complete information in one text (such as a question) and exploit it in its counterpart (such as context or passage) layer by layer. We apply FusionNet to the Stanford Question Answering Dataset (SQuAD) and it achieves the first position for both single and ensemble model on the official SQuAD leaderboard at the time of writing (Oct. 4th, 2017). Meanwhile, we verify the generalization of FusionNet with two adversarial SQuAD datasets and it sets up the new state-of-the-art on both datasets: on AddSent, FusionNet increases the best F1 metric from 46.6% to 51.4%; on AddOneSent, FusionNet boosts the best F1 metric from 56.0% to 60.7%. read more

PDF Abstract ICLR 2018 PDF ICLR 2018 Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Question Answering SQuAD1.1 FusionNet (ensemble) EM 78.978 # 77
F1 86.016 # 78
Question Answering SQuAD1.1 FusionNet (single model) EM 75.968 # 111
F1 83.900 # 111
Question Answering SQuAD1.1 dev FusionNet EM 75.3 # 18
F1 83.6 # 22
Question Answering SQuAD2.0 FusionNet++ (ensemble) EM 70.300 # 241
F1 72.484 # 246

Methods


No methods listed for this paper. Add relevant methods here