The field of machine translation (MT), the automatic translation of written text from one
natural language into another, has experienced a major paradigm shift in recent years …

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 …

Machine translation has made rapid advances in recent years. Millions of people are using it
today in online translation systems and mobile applications in order to communicate across …

This paper presents the results of the WMT17 shared tasks, which included three machine
translation (MT) tasks (news, biomedical, and multimodal), two evaluation tasks (metrics and …

We reassess a recent study (Hassan et al., 2018) that claimed that machine translation (MT)
has reached human parity for the translation of news from Chinese into English, using …

One of the difficulties of neural machine translation (NMT) is the recall and appropriate
translation of low-frequency words or phrases. In this paper, we propose a simple, fast, and …

Leveraging user-provided translation to constrain NMT has practical significance. Existing
methods can be classified into two main categories, namely the use of placeholder tags for …

Reranking models enable the integration of rich features to select a better output hypothesis
within an n-best list or lattice. These models have a long history in NLP, and we revisit …

Previous work on neural noisy channel modeling relied on latent variable models that
incrementally process the source and target sentence. This makes decoding decisions …

Neural Machine Translation (NMT) typically leverages monolingual data in training through
backtranslation. We investigate an alternative simple method to use monolingual data for …