Active Learning for Interactive Neural Machine Translation of Data Streams
This work addresses the challenge of efficient and high-quality translation for data streams, though it is incremental as it builds on existing active learning and neural machine translation techniques.
The paper tackles the problem of translating unbounded data streams by applying active learning to select sentences for human supervision, which reduces human effort and increases translation quality, with their neural system outperforming classical approaches by a large margin.
We study the application of active learning techniques to the translation of unbounded data streams via interactive neural machine translation. The main idea is to select, from an unbounded stream of source sentences, those worth to be supervised by a human agent. The user will interactively translate those samples. Once validated, these data is useful for adapting the neural machine translation model. We propose two novel methods for selecting the samples to be validated. We exploit the information from the attention mechanism of a neural machine translation system. Our experiments show that the inclusion of active learning techniques into this pipeline allows to reduce the effort required during the process, while increasing the quality of the translation system. Moreover, it enables to balance the human effort required for achieving a certain translation quality. Moreover, our neural system outperforms classical approaches by a large margin.