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 …

Abstract Machine translation is an important and challenging task that aims at automatically
translating natural language sentences from one language into another. Recently …

Organic synthesis is one of the key stumbling blocks in medicinal chemistry. A necessary yet
unsolved step in planning synthesis is solving the forward problem: Given reactants and …

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 …

The development of deep learning techniques has allowed Neural Machine Translation
(NMT) models to become extremely powerful, given sufficient training data and training time …

Deep model fusion/merging is an emerging technique that merges the parameters or
predictions of multiple deep learning models into a single one. It combines the abilities of …

Existing approaches to neural machine translation (NMT) generate the target language
sequence token-by-token from left to right. However, this kind of unidirectional decoding …

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 …

Error correction in automatic speech recognition (ASR) aims to correct those incorrect words
in sentences generated by ASR models. Since recent ASR models usually have low word …

Sentence scoring aims at measuring the likelihood score of a sentence and is widely used in
many natural language processing scenarios, like reranking, which is to select the best …