YAYI 2: Multilingual Open-Source Large Language Models.
Yin LuoQingchao KongNan XuJia CaoBao HaoBaoyu QuBo ChenChao ZhuChenyang ZhaoDonglei ZhangFan FengFeifei ZhaoHailong SunHanxuan YangHaojun PanHongyu LiuJianbin GuoJiangtao DuJingyi WangJunfeng LiLei SunLiduo LiuLifeng DongLili LiuLin WangLiwen ZhangMinzheng WangPin WangPing YuQingxiao LiRui YanRui ZouRuiqun LiTaiwen HuangXiaodong WangXiaofei WuXin PengXina ZhangXing FangXinglin XiaoYanni HaoYao DongYigang WangYing LiuYongyu JiangYungan WangYuqi WangZhangsheng WangZhaoxin YuZhen LuoWenji MaoLei WangDaniel Dajun ZengPublished in: CoRR (2023)
Keyphrases
- language model
- open source
- language modeling
- cross lingual
- n gram
- document retrieval
- information retrieval
- probabilistic model
- language independent
- language modelling
- query expansion
- retrieval model
- cross language
- context sensitive
- digital libraries
- statistical language models
- test collection
- speech recognition
- ad hoc information retrieval
- vector space model
- smoothing methods
- okapi bm
- query terms
- document length
- language model for information retrieval
- text retrieval
- cross language information retrieval
- text mining
- out of vocabulary
- relevance model
- retrieved documents
- pseudo relevance feedback
- statistical language modeling