Efficient Attention using a Fixed-Size Memory Representation

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 392–400 Copenhagen, Denmark, September 7–11, 2017. c⃝2017 Association for Computational Linguistics Efficient Attention using a Fixed-Size Memory Representation Denny Britz∗and Melody Y. Guan∗and Minh-Thang Luong Google Brain dennybritz,melodyguan,thangluong@google.com Abstract The standard content-based attention mecha- nism typically used in sequence-to-sequence models is computationally expensive as it requires the comparison of large encoder and decoder states at each time step. In this work, we propose an alternative attention mechanism based on a fixed size memory representation that is more efficient. Our technique predicts a compact set of K attention contexts during encoding and lets the decoder compute an efficient lookup that does not need to consult the memory. We show that our approach performs on-par with the standard attention mechanism while yielding inference speedups of 20% for real-world translation tasks and more for tasks with longer sequences. By visualizing attention scores we demonstrate that our models learn distinct, meaningful alignments. 1 Introduction Sequence-to-sequence models (Sutskever et al., 2014; Cho et al., 2014) have achieved state of the art results across a wide variety of tasks, including Neural Machine Translation (NMT) (Bahdanau et al., 2014; Wu et al., 2016), text summarization (Rush et al., 2015; Nallapati et al., 2016), speech recognition (Chan et al., 2015; Chorowski and Jaitly, 2016), image captioning (Xu et al., 2015), and conversational modeling (Vinyals and Le, 2015; Li et al., 2015). The most popular approaches are based on an encoder-decoder architecture consisting of two recurrent neural networks (RNNs) and an attention mechanism that aligns target to source tokens (Bah- danau et al., 2014; Luong et al., 2015). The typical attention mechanism used in these architectures computes a new attention context at each decoding ∗Equal Contribution. Author order alphabetical. step based on the current state of the decoder. Intuitively, this corresponds to looking at the source sequence after the output of every single target token. Inspired by how humans process sentences, we believe it may be unnecessary to look back at the entire original source sequence at each step.1 We thus propose an alternative attention mechanism (section 3) that leads to smaller computational time complexity. Our method predicts K attention context vectors while reading the source, and learns to use a weighted av- erage of these vectors at each step of decoding. Thus, we avoid looking back at the source sequence once it has been encoded. We show (section 4) that this speeds up inference while performing on-par with the standard mechanism on both toy and real-world WMT translation datasets. We also show that our mecha- nism leads to larger speedups as sequences get longer. Finally, by visualizing the attention scores (section 5), we verify that the proposed technique learns mean- ingful alignments, and that different attention context vectors specialize on different parts of the source. 2 Background 2.1 Sequence-to-Sequence Model with Attention Our models are based on an encoder-decoder archi- tecture with attention mechanism (Bahdanau et al., 2014; Luong et al., 2015). An encoder function …

Content truncated to 500 words