Enhance word representation for out-of-vocabulary on Ubuntu dialogue corpus.
Jianxiong DongJim HuangPublished in: CoRR (2018)
Keyphrases
- out of vocabulary
- spoken document retrieval
- word segmentation
- n gram
- hand crafted
- language model
- parallel corpora
- broadcast news
- named entity recognition
- cross language information retrieval
- spoken term detection
- statistical machine translation
- dialogue system
- multiword
- machine learning
- cross lingual
- named entities
- word sense
- sentence level
- term frequency
- word pairs
- spoken language
- document retrieval
- co occurrence
- hidden markov models
- natural language
- keywords