Efficient Attention using a Fixed-Size Memory Representation
This addresses efficiency issues for users of sequence-to-sequence models, particularly in translation, but is incremental as it builds on existing attention paradigms.
The paper tackled the computational inefficiency of standard content-based attention in sequence-to-sequence models by proposing an alternative mechanism using a fixed-size memory representation, achieving on-par performance with 20% inference speedup in translation tasks.
The standard content-based attention mechanism 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.