Identifying Word Translations from Comparable Documents Without a Seed Lexicon.
Reinhard RappSerge SharoffBogdan BabychPublished in: LREC (2012)
Keyphrases
- text corpus
- word frequencies
- concept space
- bilingual lexicon
- word spotting
- bilingual dictionaries
- keywords
- multiword
- natural language text
- document collections
- linguistic information
- related words
- printed documents
- information retrieval
- handwritten words
- information retrieval systems
- text documents
- web documents
- term frequency
- machine translation
- document retrieval
- stop words
- word pairs
- latent topics
- word frequency
- machine readable dictionaries
- xml documents
- word sense disambiguation
- n gram
- document clustering
- query translation
- query words
- retrieval systems
- spoken documents
- page layout
- relevant documents
- document analysis
- text corpora
- semantic information
- word alignment
- cross language information retrieval
- co occurrence
- multi document summarization
- natural language processing