With direct access to human-written reference as memory, retrieval-augmented generation
has achieved much progress in a wide range of text generation tasks. Since better memory …

Recently, retrieval-augmented text generation attracted increasing attention of the
computational linguistics community. Compared with conventional generation models …

It is generally believed that a translation memory (TM) should be beneficial for machine
translation tasks. Unfortunately, existing wisdom demonstrates the superiority of TM-based …

High quality end-to-end speech translation model relies on a large scale of speech-to-text
training data, which is usually scarce or even unavailable for some low-resource language …

Retrieval-augmented Neural Machine Translation models have been successful in many
translation scenarios. Different from previous works that make use of mutually similar but …

Automatic machine translation is super efficient to produce translations yet their quality is not
guaranteed. This technique report introduces TranSmart, a practical human-machine …

A translation memory (TM) is proved to be helpful to improve neural machine translation
(NMT). Existing approaches either pursue the decoding efficiency by merely accessing local …

Neural machine translation (NMT) becomes a new state-of-the-art and achieves promising
translation results using a simple encoder-decoder neural network. This neural network is …

The integration of machine translation in the human translation work flow rises intriguing and
challenging research issues. One of them, addressed in this work, is how to dynamically …

In statistical machine translation (SMT), the optimization of the system parameters to
maximize translation accuracy is now a fundamental part of virtually all modern systems. In …