DARWIN Series: Domain Specific Large Language Models for Natural Science.
Tong XieYuwei WanWei HuangZhenyu YinYixuan LiuShaozhou WangQingyuan LinghuChunyu KitClara GrazianWenjie ZhangImran RazzakBram HoexPublished in: CoRR (2023)
Keyphrases
- language model
- domain specific
- language modeling
- document retrieval
- n gram
- probabilistic model
- speech recognition
- information retrieval
- language modelling
- retrieval model
- query expansion
- relevance model
- smoothing methods
- statistical language models
- pseudo relevance feedback
- test collection
- context sensitive
- language models for information retrieval
- document ranking
- ad hoc information retrieval
- spoken term detection
- query terms
- word error rate
- document length
- translation model