On Statistical Machine Translation and Translation Theory
2015 (English)In: Proceedings of the Second Workshop on Discourse in Machine Translation (DiscoMT), Stroudsburg, PA: Association for Computational Linguistics, 2015, 168-172 p.Conference paper (Refereed)
The translation process in statistical machine translation (SMT) is shaped by technical constraints and engineering considerations. SMT explicitly models translation as search for a target-language equivalent of the input text. This perspective on translation had wide currency in mid-20th century translation studies, but has since been superseded by approaches arguing for a more complex relation between source and target text. In this paper, we show how traditional assumptions of translational equivalence are embodied in SMT through the concepts of word alignment and domain and discuss some limitations arising from the word-level/corpus-level dichotomy inherent in these concepts.
Place, publisher, year, edition, pages
Stroudsburg, PA: Association for Computational Linguistics, 2015. 168-172 p.
Language Technology (Computational Linguistics)
Research subject Computational Linguistics
IdentifiersURN: urn:nbn:se:uu:diva-262367ISBN: 978-1-941643-32-7OAI: oai:DiVA.org:uu-262367DiVA: diva2:853692
Second Workshop on Discourse in Machine Translation (DiscoMT), 17 September 2015, Lisbon, Portugal