Attribute-controlled translation (ACT) is a subtask of machine translati...
Like many other machine learning applications, neural machine translatio...
As generic machine translation (MT) quality has improved, the need for
t...
Sockeye 3 is the latest version of the Sockeye toolkit for Neural Machin...
The machine translation (MT) task is typically formulated as that of
ret...
The training data used in NMT is rarely controlled with respect to speci...
Database systems analyze queries to determine upfront which data is need...
While Iterative Back-Translation and Dual Learning effectively incorpora...
We present Sockeye 2, a modernized and streamlined version of the Sockey...
Neural Machine Translation (NMT) models are sensitive to small perturbat...
This work aims to produce translations that convey source language conte...
Despite some empirical success at correcting exposure bias in machine
tr...
Snapshot semantics is widely used for evaluating queries over temporal d...
We aim to better exploit the limited amounts of parallel text available ...
Generating natural language requires conveying content in an appropriate...
Despite impressive progress in high-resource settings, Neural Machine
Tr...
A well-established technique for capturing database provenance as annota...
Recognizing that even correct translations are not always semantically
e...
Debugging transactions and understanding their execution are of immense
...