2005. Models for inuktitut-english word alignment
This paper presents a set of techniques for bitext word align-ment, optimized for a language pair with the characteristics of Inuktitut-English. The resulting systems exploit cross-lingual afnities at the sublexical level of syllables and substrings, as well as regular patterns of transliteration an...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Text |
| Language: | English |
| Subjects: | |
| Online Access: | http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.594.9060 http://www.mt-archive.info/ACL-2005-Schafer.pdf |
| Summary: | This paper presents a set of techniques for bitext word align-ment, optimized for a language pair with the characteristics of Inuktitut-English. The resulting systems exploit cross-lingual afnities at the sublexical level of syllables and substrings, as well as regular patterns of transliteration and the tendency to-wards monotonicity of alignment. Our most successful systems were based on classier combination, and we found different combination methods performed best under the target evalua-tion metrics of F-measure and alignment error rate. 1 |
|---|