Paper Info
Title
Mining the Web to Create a Language Model for Mapping between English Names and Phrases and Japanese
Abstract
The Web provides the largest, exploitable collection of language use. If we can mine the Web to build abstract models of language use, these models may have many applications. Here we present one example of using the implicit intelligence of language use to solve an important problem for machine translation programs and cross-lingual applications. This problem involves the translation of words written in katakana characters in Japanese. In this paper, we describe techniques of discovering katakana transliteration of English names and of finding English translations of multiword katakana sequences using implicit language models of English and Japanese found on the Web. These techniques were evaluated against human-constructed English-katakana glosses.
Year
DOI
Venue
2004
10.1109/WI.2004.99
Web Intelligence
Keywords
Field
DocType
katakana transliteration,multiword katakana,important problem,implicit language model,english names,implicit intelligence,english translation,katakana character,language model,language use,english name,machine translation program,natural languages,gold,dictionaries,data mining,natural language processing,writing,machine intelligence,machine translation,information retrieval
Cache language model,World Wide Web,Computer science,Computational linguistics,Machine translation,Natural language,Natural language processing,Universal Networking Language,Language identification,Artificial intelligence,Language model,Katakana
Conference
ISBN
Citations 
PageRank 
0-7695-2100-2
10
0.68
References 
Authors
4
3
Name
Order
Citations
PageRank
Gregory Grefenstette11129147.00
Yan Qu2100.68
David A. Evans3841147.89