China
Africa
Explore chapters and articles related to this topic
Results and Conclusions
Published in Krzysztof Wołk, Machine Learning in Translation Corpora Processing, 2019
Moses is a tool environment for statistical machine translation that enables users to train translation models for any two languages. This implementation of the statistical approach to machine translation is currently the dominant approach in this field of research [13].
Unsupervised SMT: an analysis of Indic languages and a low resource language
Published in Journal of Experimental & Theoretical Artificial Intelligence, 2022
Shefali Saxena, Shweta Chauhan, Paras Arora, Philemon Daniel
To our awareness, there has been no prior attempt at unsupervised statistical MT for low resource Himachali language. Researchers in this area have already built several MT systems in various languages and domains. MT for Indian languages, on the other hand, is still in inception. Google Translator is a free SMT service offered by Google Inc. that allows converting a portion of text, a web page, or a document to a different domain (Kumar & Goyal, 2018). Phrase-based models consider the translation unit a phrase and are implemented using the Pharaoh Toolkit and an open-source toolkit (Koehn et al., 2007), Moses.
Ambient intelligence framework for real-time speech-to-sign translation
Published in Assistive Technology, 2018
Mwaffaq Otoom, Mohammad A. Alzubaidi
Machine translation has long been used to translate between different languages (Brown et al., 1990). Having the corpus of each language of interest, machine translation uses mainly rules, examples, or statistical methods to translate between the two corpora. For this article, we used the popular free, open source toolkit Moses (Och & Ney, 2003) to translate English sentences recognized by the speech recognition algorithm to ASL glosses. Moses is a phrase-based SMT system that uses parallel corpora for training purposes.