Automatic metrics play a crucial role in machine translation. Despite th...
In speech translation, leveraging multimodal data to improve model
perfo...
Benefiting from the sequence-level knowledge distillation, the
Non-Autor...
The advancement of audio-language (AL) multimodal learning tasks has bee...
This paper introduces GigaST, a large-scale pseudo speech translation (S...
This paper presents Self-correcting Encoding (Secoco), a framework that
...
This paper describes the systems submitted to IWSLT 2021 by the Volctran...
Developing a unified multilingual translation model is a key topic in ma...
Automatic translation of dialogue texts is a much needed demand in many ...
Fine-tuning is a major approach for domain adaptation in Neural Machine
...
NeurST is an open-source toolkit for neural speech translation developed...
Discourse context has been proven useful when translating documents. It ...
Neural models for text generation require a softmax layer with proper to...
GPT-2 and BERT demonstrate the effectiveness of using pre-trained langua...