Character and Subword-Based Word Representation for Neural Language Modeling Prediction.
Matthieu LabeauAlexandre AllauzenPublished in: SWCN@EMNLP (2017)
Keyphrases
- language modeling
- n gram
- language model
- word segmentation
- statistical language modeling
- term weighting
- information retrieval
- query expansion
- retrieval model
- cross lingual
- text classification
- translation model
- probabilistic model
- speech recognition
- neural network
- out of vocabulary
- language independent
- improvements in retrieval effectiveness
- test collection
- knowledge discovery
- digital libraries
- comparable corpora
- spoken document retrieval
- data mining