Exploring Bilingual Word Vectors for Hindi-English Cross-Language Information Retrieval.
Vijay Kumar SharmaNamita MittalPublished in: ICIA (2016)
Keyphrases
- cross language information retrieval
- comparable corpora
- machine translation
- statistical machine translation
- english chinese
- source language
- query translation
- bilingual dictionaries
- parallel corpus
- translation model
- bilingual lexicon
- proper names
- parallel corpora
- word pairs
- cross language
- sense disambiguation
- chinese english
- word alignment
- out of vocabulary
- cross lingual
- machine translation system
- target language
- character n grams
- word sense disambiguation
- terminology extraction
- language resources
- parallel texts
- query words
- language specific
- word level
- cross language retrieval
- linguistic resources
- machine transliteration
- language independent
- translation probabilities
- vector space
- co occurrence
- machine learning
- information extraction
- named entity recognition
- natural language
- query terms
- news articles
- text retrieval
- semantic relations
- question answering
- document collections
- document retrieval
- multilingual information retrieval
- keywords