We introduce a model for constructing vector representations of words by composing
characters using bidirectional LSTMs. Relative to traditional word representation models that …

k-Nearest-Neighbor Machine Translation (kNN-MT) has been recently proposed as a non-
parametric solution for domain adaptation in neural machine translation (NMT). It aims to …

Abstract We propose Bilingually-constrained Recursive Auto-encoders (BRAE) to learn
semantic phrase embeddings (compact vector representations for phrases), which can …

For a given training corpus of parallel sentences, the quality of the output produced by a
translation system relies heavily on the underlying similarity measurement criteria. A phrase …

Although more additional corpora are now available for Statistical Machine Translation
(SMT), only the ones which belong to the same or similar domains with the original corpus …

In the last years, researchers conducted several studies to evaluate the machine translation
quality based on the relationship between word alignments and phrase table. However …

This paper describes our experience using available linguistic resources for Croatian in
order to address data sparseness when building an English-to-Croatian general domain …

A widely used automatic translation approach, phrase-based statistical machine translation,
learns a probabilistic translation model composed of phrases from a large parallel corpus …

In this paper we address the problem of automatic acquisition of a human-oriented
translation dictionary from a large-scale parallel corpus. The initial translation equivalents …

A computer-implemented technique includes receiving, at a server including one or more
processors, a phrase table for statistical machine translation, the phrase table including a …