Investigating the effect of sub-word segmentation on the performance of transformer language models.
Jue HouAnisia KatinskaiaAnh-Duc VuRoman YangarberPublished in: CoRR (2023)
Keyphrases
- language model
- word segmentation
- n gram
- language modeling
- statistical language modeling
- probabilistic model
- document retrieval
- information retrieval
- handwriting recognition
- speech recognition
- language independent
- retrieval model
- query expansion
- cross lingual
- word recognition
- out of vocabulary
- test collection
- vector space model
- text classification
- relevance model
- translation model
- document ranking
- part of speech
- word level
- smoothing methods
- pseudo relevance feedback
- information retrieval systems
- language models for information retrieval