On Statistical Machine Translation and Translation Theory

Christian Hardmeier

Research output: Chapter in Book/Report/Conference proceedingConference contribution


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 This perspective on translation had wide currency in mid-20th century translation studies, but has since been superseded by approaches arguing for a more complex relation between source and target text.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.
Original languageEnglish
Title of host publicationProceedings of the Second Workshop on Discourse in Machine Translation
Place of PublicationLisbon, Portugal
PublisherAssociation for Computational Linguistics
Number of pages5
ISBN (Electronic)978-1-941643-32-7
Publication statusPublished - 21 Sep 2015
EventSecond Workshop on Discourse in Machine Translation - Lisbon, Portugal
Duration: 17 Sep 201517 Sep 2015


WorkshopSecond Workshop on Discourse in Machine Translation
Abbreviated titleDiscoMT 2015
Internet address

Fingerprint Dive into the research topics of 'On Statistical Machine Translation and Translation Theory'. Together they form a unique fingerprint.

Cite this