Abstract | ||
---|---|---|
Translation of named entities (NEs), such as person names, organization names and location names is crucial for cross lingual information retrieval, machine translation, and many other natural language processing applications. Newly named entities are introduced on daily basis in newswire and this greatly complicates the translation task. Also, while some names can be translated, others must be transliterated, and, still, others are mixed. In this paper we introduce an integrated approach for named entity translation deploying phrase-based translation, word-based translation, and transliteration modules into a single framework. While Arabic based, the approach introduced here is a unified approach that can be applied to NE translation for any language pair. |
Year | Venue | Keywords |
---|---|---|
2005 | SEMITIC@ACL | unified approach,translation task,integrated approach,entity translation,word-based translation,phrase-based translation,language pair,machine translation,ne translation,natural language processing application,natural language processing,information retrieval |
Field | DocType | Citations |
Entity linking,Rule-based machine translation,Example-based machine translation,Computer science,Machine translation,Phrase,Named entity,Natural language processing,Artificial intelligence,Computer-assisted translation,Transliteration | Conference | 10 |
PageRank | References | Authors |
0.62 | 8 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hany Hassan | 1 | 277 | 26.16 |
Jeffrey Sorensen | 2 | 10 | 0.62 |