Trivial transfer learning for low-resource neural machine translation
Transfer learning has been proven as an effective technique for neural machine translation
under low-resource conditions. Existing methods require a common target language …
under low-resource conditions. Existing methods require a common target language …
Exploring benefits of transfer learning in neural machine translation
T Kocmi - arXiv preprint arXiv:2001.01622, 2020 - arxiv.org
Neural machine translation is known to require large numbers of parallel training sentences,
which generally prevent it from excelling on low-resource language pairs. This thesis …
which generally prevent it from excelling on low-resource language pairs. This thesis …
[PDF][PDF] Improving machine translation via triangulation and transliteration
In this paper we improve Urdu→ Hindi⇄ English machine translation through triangulation
and transliteration. First we built an Urdu→ Hindi SMT system by inducing triangulated and …
and transliteration. First we built an Urdu→ Hindi SMT system by inducing triangulated and …
Slavic languages in phrase-based statistical machine translation: a survey
The demand for translations is increasing at a rate far beyond the capacity of professional
translators. It is too difficult, time consuming and expensive to translate everything from …
translators. It is too difficult, time consuming and expensive to translate everything from …
[图书][B] Machine Translation and Transliteration involving Related, Low-resource Languages
A Kunchukuttan, P Bhattacharyya - 2021 - taylorfrancis.com
Machine Translation and Transliteration involving Related, Low-resource Languages
discusses an important aspect of natural language processing that has received lesser …
discusses an important aspect of natural language processing that has received lesser …
The reality of multi-lingual machine translation
Our book" The Reality of Multi-Lingual Machine Translation" discusses the benefits and
perils of using more than two languages in machine translation systems. While focused on …
perils of using more than two languages in machine translation systems. While focused on …
[PDF][PDF] Pivoting methods and data for czech-vietnamese translation via english
DT Hoang, O Bojar - Proceedings of the 19th Annual Conference …, 2016 - aclanthology.org
The statistical approach to machine translation (MT) relies heavily on large parallel corpora.
For many language pairs, this can be a significant obstacle. A promising alternative is …
For many language pairs, this can be a significant obstacle. A promising alternative is …
[PDF][PDF] PhraseFix: Statistical post-editing of TectoMT
We present two English-to-Czech systems that took part in the WMT 2013 shared task:
TECTOMT and PHRASEFIX. The former is a deep-syntactic transfer-based system, the latter …
TECTOMT and PHRASEFIX. The former is a deep-syntactic transfer-based system, the latter …