On the Locality of Attention in Direct Speech Translation
This addresses efficiency bottlenecks in direct speech translation for NLP applications, but it is incremental as it modifies existing attention mechanisms.
The paper tackles the quadratic complexity of self-attention in Transformers for long sequences like speech by analyzing local patterns in attention weights and proposing a local efficient attention method. The result is a model that matches baseline performance while improving efficiency by skipping unnecessary computations.
Transformers have achieved state-of-the-art results across multiple NLP tasks. However, the self-attention mechanism complexity scales quadratically with the sequence length, creating an obstacle for tasks involving long sequences, like in the speech domain. In this paper, we discuss the usefulness of self-attention for Direct Speech Translation. First, we analyze the layer-wise token contributions in the self-attention of the encoder, unveiling local diagonal patterns. To prove that some attention weights are avoidable, we propose to substitute the standard self-attention with a local efficient one, setting the amount of context used based on the results of the analysis. With this approach, our model matches the baseline performance, and improves the efficiency by skipping the computation of those weights that standard attention discards.