GeoGalactica: A Scientific Large Language Model in Geoscience.
Zhouhan LinCheng DengLe ZhouTianhang ZhangYi XuYutong XuZhongmou HeYuanyuan ShiBeiya DaiYunchong SongBoyi ZengQiyuan ChenTao ShiTianyu HuangYiwei XuShu WangLuoyi FuWeinan ZhangJunxian HeChao MaYunqiang ZhuXinbing WangChenghu ZhouPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- probabilistic model
- document retrieval
- query expansion
- inquiry skills
- speech recognition
- language modelling
- information retrieval
- retrieval model
- query terms
- test collection
- statistical language models
- smoothing methods
- document ranking
- mixture model
- ad hoc information retrieval
- context sensitive
- pseudo relevance feedback
- translation model
- vector space model
- data mining
- word error rate
- co occurrence
- language model for information retrieval
- cross language
- query specific
- document length
- retrieval effectiveness
- relevant documents