Models for Inuktitut-English word alignment
Charles Schafer, Elliott Franco Drábek · 2005
This paper presents a set of techniques for bitext word alignment, optimized for a language pair with the characteristics of Inuktitut-English. The resulting systems exploit cross-lingual affinities at the sublexical level of syllables and substrings, as well as regular patterns of transliteration and the tendency towards monotonicity of alignment. Our most successful systems were based on classifier combination, and we found different combination methods performed best under the target evaluation metrics of F-measure and alignment error rate.