Active Learning for Interactive Neural Machine Translation of Data Streams
By Álvaro Peris, Francisco Casacuberta. 2018
61 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Yejin Choi
- Noah A. Smith
- Mohit Bansal
- Hannaneh Hajishirzi
- Luke S. Zettlemoyer
- Swabha Swayamdipta
- Jonathan Berant
- Percy Liang
Citations in the corpus
- Continual Lifelong Learning in Natural Language Processing: A Survey (2020, background): “However, some attempts have been made (e.g. Peris and Casacuberta, 2018; Liu et al., 2018; Kaiser et al., 2017; Tu et al., 2018).”
- Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics (2020, methodology): “Our methods are also reminiscent of active learning methods (Settles, 2009; Peris and Casacuberta, 2018; P.V.S and Meyer, 2019), such as uncertainty sampling (Lewis and Gale, 1994) which selects (unlabeled) data points, which a model trained on a small labeled subset, has least confidence in, or pre”