Fixed and Adaptive Simultaneous Machine Translation Strategies Using Adapters
Simultaneous machine translation aims at solving the task of real-time translation by starting to translate before consuming the full input, which poses challenges in terms of balancing quality and latency of the translation. The wait-$k$ policy offers a solution by starting to translate after consuming $k$ words, where the choice of the number $k$ directly affects the latency and quality. In applications where we seek to keep the choice over latency and quality at inference, the wait-$k$ policy obliges us to train more than one model. In this paper, we address the challenge of building one model that can fulfil multiple latency levels and we achieve this by introducing lightweight adapter modules into the decoder. The adapters are trained to be specialized for different wait-$k$ values and compared to other techniques they offer more flexibility to allow for reaping the benefits of parameter sharing and minimizing interference. Additionally, we show that by combining with an adaptive strategy, we can further improve the results. Experiments on two language directions show that our method outperforms or competes with other strong baselines on most latency values.
Code (1)
Tasks
DecoderMachine TranslationTranslationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Turning Fixed to Adaptive: Integrating Post-Evaluation into Simultaneous Machine Translation
Simultaneous machine translation (SiMT) starts its translation before reading the whole source sentence and employs either fixed or adaptive policy to generate the target sentence. Compared to the fixed policy, the adapt…
Machine TranslationSentenceTranslationExploiting Multimodal Reinforcement Learning for Simultaneous Machine Translation
This paper addresses the problem of simultaneous machine translation (SiMT) by exploring two main concepts: (a) adaptive policies to learn a good trade-off between high translation quality and low latency; and (b) visual…
Machine Translationreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1Data-Driven Adaptive Simultaneous Machine Translation
In simultaneous translation (SimulMT), the most widely used strategy is the wait-k policy thanks to its simplicity and effectiveness in balancing translation quality and latency. However, wait-k suffers from two major li…
Machine TranslationSentenceTranslationData-Driven Adaptive Simultaneous Machine Translation
In simultaneous translation (SimulMT), the most widely used strategy is the \waitk policy thanks to its simplicity and effectiveness in balancing translation quality and latency. However, \waitk suffers from two major li…
Machine TranslationSentenceTranslationSimultaneous Translation Policies: From Fixed to Adaptive
Adaptive policies are better than fixed policies for simultaneous translation, since they can flexibly balance the tradeoff between translation quality and latency based on the current context information. But previous m…
SentenceTranslation