Input Augmentation Improves Constrained Beam Search for Neural Machine Translation: NTT at WAT 2021
This work addresses the challenge of generating translations that include specific word constraints, which is important for applications like controlled text generation, but it is incremental as it builds on existing constrained beam search methods.
The paper tackled the problem of constrained neural machine translation by combining input augmentation with constrained beam search, resulting in improved translation accuracy and reduced inference time while meeting all word constraints, achieving the best automatic evaluation scores for both English-Japanese and Japanese-English directions.
This paper describes our systems that were submitted to the restricted translation task at WAT 2021. In this task, the systems are required to output translated sentences that contain all given word constraints. Our system combined input augmentation and constrained beam search algorithms. Through experiments, we found that this combination significantly improves translation accuracy and can save inference time while containing all the constraints in the output. For both En->Ja and Ja->En, our systems obtained the best evaluation performances in automatic evaluation.