Graph-Based Bilingual Sentence Alignment from Large Scale Web Pages.
Yihe ZhuHaofen WangXixiu OuyangYong YuPublished in: NLDB (2011)
Keyphrases
- sentence pairs
- web pages
- word alignment
- parallel corpus
- website
- word level
- search engine
- machine translation
- web page classification
- web documents
- web search engines
- statistical machine translation
- keywords
- machine translation system
- word pairs
- cross lingual
- web content
- parallel corpora
- semi supervised
- cross language information retrieval
- web search
- chinese english
- parallel texts
- natural language
- cross language
- link analysis
- data records
- web server
- document images
- co occurrence