CompoundPiece: Evaluating and Improving Decompounding Performance of Language Models.
Benjamin MinixhoferJonas PfeifferIvan VulicPublished in: CoRR (2023)
Keyphrases
- language model
- test collection
- language modeling
- n gram
- retrieval model
- document retrieval
- probabilistic model
- statistical language models
- information retrieval
- language modelling
- speech recognition
- query expansion
- ad hoc information retrieval
- context sensitive
- vector space model
- language independent
- smoothing methods
- pseudo relevance feedback
- language model for information retrieval
- document ranking
- relevance model
- retrieval effectiveness
- query terms
- relevant documents
- language models for information retrieval
- translation model
- cross language
- word error rate
- feature selection