Abstract | ||
---|---|---|
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. |
Year | Venue | Keywords |
---|---|---|
2005 | ParallelText@ACL | different combination method,classifier combination,sublexical level,target evaluation metrics,inuktitut-english word alignment,alignment error rate,language pair,successful system,regular pattern,cross-lingual affinity,bitext word alignment |
Field | DocType | Volume |
Substring,Computer science,Bitext word alignment,Word error rate,Speech recognition,Exploit,Artificial intelligence,Natural language processing,Inuktitut,Classifier (linguistics),Transliteration | Conference | W05-08 |
Citations | PageRank | References |
3 | 0.48 | 4 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Charles Schafer | 1 | 168 | 12.05 |
Elliott Franco Drábek | 2 | 206 | 16.02 |