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