Code-Switching Language Modeling with Bilingual Word Embeddings: A Case Study for Egyptian Arabic-English.
Injy HamedMoritz ZhuMohamed ElmahdySlim AbdennadherNgoc Thang VuPublished in: SPECOM (2019)
Keyphrases
- language modeling
- cross lingual
- parallel corpus
- language model
- n gram
- translation model
- comparable corpora
- word segmentation
- word sense
- unknown words
- word alignment
- statistical machine translation
- retrieval model
- cross language
- query expansion
- bilingual dictionaries
- statistical language modeling
- information retrieval
- multiword
- language independent
- parallel corpora
- vector space
- probabilistic model
- machine translation system
- source language
- character n grams
- machine translation
- out of vocabulary
- english chinese
- dimensionality reduction
- sentence pairs
- cross language information retrieval
- query translation
- document retrieval
- relevance model
- handwriting recognition
- text classification
- translation probabilities
- arabic documents
- target language
- language identification
- finite state transducers
- word level
- low dimensional
- relevant documents
- term frequency
- bayesian networks
- search engine
- test collection