Similarity scoring for recognizing repeated out-of-vocabulary words.
Mirko HannemannStefan KombrinkMartin KarafiátLukás BurgetPublished in: INTERSPEECH (2010)
Keyphrases
- out of vocabulary
- language model
- n gram
- word segmentation
- spoken document retrieval
- named entity recognition
- broadcast news
- cross language information retrieval
- parallel corpora
- hand crafted
- cross lingual
- similarity measure
- named entities
- semantic similarity
- query terms
- term frequency
- word pairs
- language modeling
- language independent
- information extraction
- machine translation
- retrieval model
- wordnet
- text classification
- document retrieval
- text categorization
- natural language processing