Interactive Attention for Neural Machine Translation

Understand

Conventional attention-based Neural Machine Translation (NMT) conducts dynamic alignment in generating the target sentence.

• By repeatedly reading the representation of source sentence, which keeps fixed after generated by the encoder (Bahdanau et al., 2015), the attention mechanism has greatly enhanced state-of-the-art NMT.
• In this paper, we propose a new attention mechanism, called INTERACTIVE ATTENTION, which models the interaction between the decoder and the representation of source sentence during translation by both reading and writing operations.
• INTERACTIVE ATTENTION can keep track of the interaction history and therefore improve the translation performance.