Handling Out-Of-Vocabulary Problem in Hangeul Word Embeddings.
Ohjoon KwonDohyun KimSoo-Ryeon LeeJunyoung ChoiSangKeun LeePublished in: EACL (2021)
Keyphrases
- out of vocabulary
- word segmentation
- n gram
- language model
- spoken document retrieval
- named entity recognition
- cross language information retrieval
- broadcast news
- query words
- parallel corpora
- named entities
- cross lingual
- query terms
- language independent
- hand crafted
- vector space
- term frequency
- spoken term detection
- previously unseen
- test collection
- query expansion
- word recognition
- language modeling
- information retrieval
- maximum entropy
- low dimensional
- natural language processing
- cross language
- retrieval model
- document retrieval
- word level
- conditional random fields
- co occurrence
- probabilistic model