Translating into Free Word Order Languages
Abstract
In this paper, I discuss machine translation of English text into Turkish, a relatively ``free'' word order language. I present algorithms that determine the topic and the focus of each target sentence (using salience (Centering Theory), old vs. new information, and contrastiveness in the discourse model) in order to generate the contextually appropriate word orders in the target language.
- Publication:
-
arXiv e-prints
- Pub Date:
- April 1996
- DOI:
- arXiv:
- arXiv:cmp-lg/9604020
- Bibcode:
- 1996cmp.lg....4020H
- Keywords:
-
- Computer Science - Computation and Language
- E-Print:
- COLING 1996, latex, 6 pages, colap = aclap = eaclap.sty