IrokoBench: A New Benchmark for African Languages in the Age of Large Language Models.
David Ifeoluwa AdelaniJessica OjoIsrael Abebe AzimeJian Yun ZhuangJesujoba O. AlabiXuanli HeMillicent OchiengSara HookerAndiswa BukulaEn-Shiun Annie LeeChiamaka ChukwunekeHappy BuzaabaBlessing K. SibandaGodson KalipeJonathan MukiibiSalomon KabongoFoutse YuehgohMmasibidi SetakaLolwethu NdolelaNkiruka OduRooweither MabuyaShamsuddeen Hassan MuhammadSalomey OseiSokhar SambTadesse Kebede GugePontus StenetorpPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- cross lingual
- language independent
- probabilistic model
- document retrieval
- retrieval model
- test collection
- information retrieval
- speech recognition
- language modelling
- query terms
- query expansion
- context sensitive
- language models for information retrieval
- ad hoc information retrieval
- statistical language models
- translation model
- document ranking
- vector space model
- smoothing methods
- pseudo relevance feedback
- document level
- text summarization
- text categorization
- retrieval effectiveness