When translating “The secretary asked for details.” to a language with grammatical gender, it
might be necessary to determine the gender of the subject “secretary”. If the sentence does …

Most of the recent work on terminology integration in machine translation has assumed that
terminology translations are given already inflected in forms that are suitable for the target …

The paper describes the development process of the Tilde's NMT systems that were
submitted for the WMT 2018 shared task on news translation. We describe the data filtering …

The paper describes parallel corpus filtering methods that allow reducing noise of noisy
“parallel” corpora from a level where the corpora are not usable for neural machine …

Neural machine translation systems typically are trained on curated corpora and break when
faced with non-standard orthography or punctuation. Resilience to spelling mistakes and …

This paper describes Tilde's work on the development of a Neural Machine Translation
(NMT) platform for Hieronymus, a Switzerland-based boutique legal and financial translation …

In this paper, we describe the development of the EU Council Presidency Translator, a
machine translation solution first introduced during the EU Council Presidency of Latvia. We …

Machine Learning in Translation introduces machine learning (ML) theories and
technologies that are most relevant to translation processes, approaching the topic from a …

This thesis aims to address major concerns created by the rapid pace of development in
natural language processing (NLP). Developments to state-of-the-art in NLP have been …