Attention Forcing for Sequence-to-sequence Model Training

A BSTRACT Auto-regressive sequence-to-sequence models with attention mechanism have achieved state-of-the-art performance in many tasks such as machine translation and speech synthesis. These models can be difficult to train. The problem is that the model is unlikely to recover from its mistakes during inference, where the reference output is replaced by generated output. Several approaches deal with this problem, largely by guiding the model with generated output history. To make training stable, these approaches often require a heuristic schedule or an auxiliary classifier. This paper introduces attention forcing, which guides the model with generated output history and reference attention. This approach can train the model to recover from its mistakes, in a stable fashion, without the need for a schedule or a classifier. In addition, it allows the model to generate output sequences aligned with the references, which can be important for cascaded systems like many speech synthesis systems. Experiments on machine translation show that for tasks where various reorderings of the output are valid, guiding the model with generated output history is challenging, while guiding the model with reference attention is beneficial. 1 I NTRODUCTION Auto-regressive sequence-to-sequence (seq2seq) models with attention mechanism are widely used in a variety of areas including Neural Machine Translation (NMT) (Neubig, 2017; Huang et al., 2016) and speech synthesis (Shen et al., 2018; Wang et al., 2018), also known as Text-To-Speech (TTS). These models excel at connecting sequences of different length, but can be difficult to train. A standard approach is teacher forcing, which guides a model with reference output history during training.