Learning to Actively Learn Neural Machine Translation
By Ming Liu, Wray L. Buntine, Gholamreza Haffari. 2018
40 citations recorded by the source corpus.
Traditional active learning (AL) methods for machine translation (MT) rely on heuristics. However, these heuristics are limited when the characteristics of the MT problem change due to e.g. the language pair or the amount of the initial bitext. In this paper, we present a framework to learn sentence selection strategies for neural MT. We train the AL query strategy using a high-resource language-pair based on AL simulations, and then transfer it to the low-resource language-pair of interest. The learned query strategy capitalizes on the shared characteristics between the language pairs to make an effective use of the AL budget. Our experiments on three language-pairs confirms that our method is more effective than strong heuristic-based methods in various conditions, including cold-start and warm-start as well as small and extremely small data conditions.
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
- Colin Cherry
- Marta Ruiz Costa-jussà
- George F. Foster
- Magdalena Biesialska
- Katarzyna Biesialska
- Maxim Krikun
- Manish Kumar
- Orhan Firat
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).”
- Reinforcement Learning based Curriculum Optimization for Neural Machine Translation (2019, background): “Finally, Liu et al. (2018) apply imitation learning to actively select monolingual training sentences for labeling in NMT, and show that the learned strategy can be transferred to a related language pair.”