Attentive Pooling Networks

11 Feb 2016  ·  Cicero dos Santos, Ming Tan, Bing Xiang, Bo-Wen Zhou ·

In this work, we propose Attentive Pooling (AP), a two-way attention mechanism for discriminative model training. In the context of pair-wise ranking or classification with neural networks, AP enables the pooling layer to be aware of the current input pair, in a way that information from the two input items can directly influence the computation of each other's representations. Along with such representations of the paired inputs, AP jointly learns a similarity measure over projected segments (e.g. trigrams) of the pair, and subsequently, derives the corresponding attention vector for each input to guide the pooling. Our two-way attention mechanism is a general framework independent of the underlying representation learning, and it has been applied to both convolutional neural networks (CNNs) and recurrent neural networks (RNNs) in our studies. The empirical results, from three very different benchmark tasks of question answering/answer selection, demonstrate that our proposed models outperform a variety of strong baselines and achieve state-of-the-art performance in all the benchmarks.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Question Answering SemEvalCQA AP-CNN P@1 0.755 # 2
MAP 0.771 # 5
Question Answering WikiQA AP-CNN MAP 0.6886 # 9
MRR 0.6957 # 12
Question Answering YahooCQA AP-CNN P@1 0.560 # 5
MRR 0.726 # 5
Question Answering YahooCQA AP-BiLSTM P@1 0.568 # 4
MRR 0.731 # 4

Methods


No methods listed for this paper. Add relevant methods here