German Text Simplification: Finetuning Large Language Models with Semi-Synthetic Data.
Lars KlöserMika BeeleJan-Niklas SchagenBodo KraftPublished in: CoRR (2024)
Keyphrases
- synthetic data
- language model
- information retrieval
- language modeling
- n gram
- document level
- retrieval model
- query expansion
- document retrieval
- probabilistic model
- language modelling
- speech recognition
- text retrieval
- statistical language models
- multiword
- context sensitive
- real world
- real image data
- language model for information retrieval
- database
- language models for information retrieval
- data sets
- keywords
- text mining
- query terms
- test collection
- vector space model
- relevance model
- text documents
- improve retrieval effectiveness
- smoothing methods
- query specific
- out of vocabulary
- co occurrence
- pseudo relevance feedback
- document ranking
- web documents
- cross language