Neural Machine Translation with Recurrent Attention Modeling
This work addresses translation accuracy for machine translation systems, but it is incremental as it builds upon existing attention models.
The paper tackles the problem of improving neural machine translation by modeling the relationship between past and future attention levels using recurrent networks per input word, resulting in improved translation quality.
Knowing which words have been attended to in previous time steps while generating a translation is a rich source of information for predicting what words will be attended to in the future. We improve upon the attention model of Bahdanau et al. (2014) by explicitly modeling the relationship between previous and subsequent attention levels for each word using one recurrent network per input word. This architecture easily captures informative features, such as fertility and regularities in relative distortion. In experiments, we show our parameterization of attention improves translation quality.