Integrating Cross-Lingually Relevant News Articles and Monolingual Web Documents in Bilingual Lexicon Acquisition.
Takehito UtsuroKohei HinoMitsuhiro KidaSeiichi NakagawaSatoshi SatoPublished in: COLING (2004)
Keyphrases
- web documents
- news articles
- comparable corpora
- cross lingual
- text documents
- information extraction
- cross language information retrieval
- keywords
- cross language
- web search engines
- machine translation
- web pages
- document representation
- link structure
- domain specific
- parallel corpora
- n gram
- information retrieval
- question answering
- document collections
- information retrieval systems
- vector space model
- natural language