Discovering machine translation strategies beyond word-for-word translation: a laboratory assignment

Juan Antonio Pérez-Ortiz, Mikel L. Forcada


Abstract
It is a common mispreconception to say that machine translation programs translate word-for-word, but real systems follow strategies which are much more complex. This paper proposes a laboratory assignment to study the way in which some commercial machine translation programs translate whole sentences and how the translation differs from a word-for-word translation. Students are expected to infer some of these extra strategies by observing the outcome of real systems when translating a set of sentences designed on purpose. The assignment also makes students aware of the difficulty of constructing such programs while bringing some technological light into the apparent “magic” of machine translation.
Anthology ID:
2001.mtsummit-teach.7
Volume:
Workshop on Teaching Machine Translation
Month:
September 18-22
Year:
2001
Address:
Santiago de Compostela, Spain
Editors:
Mikel L. Forcada, Juan Antonio Pérez-Ortiz
Venue:
MTSummit
SIG:
Publisher:
Note:
Pages:
Language:
URL:
https://aclanthology.org/2001.mtsummit-teach.7
DOI:
Bibkey:
Cite (ACL):
Juan Antonio Pérez-Ortiz and Mikel L. Forcada. 2001. Discovering machine translation strategies beyond word-for-word translation: a laboratory assignment. In Workshop on Teaching Machine Translation, Santiago de Compostela, Spain.
Cite (Informal):
Discovering machine translation strategies beyond word-for-word translation: a laboratory assignment (Pérez-Ortiz & Forcada, MTSummit 2001)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-bitext-workshop/2001.mtsummit-teach.7.pdf