ALLaM: Large Language Models for Arabic and English.
M. Saiful BariYazeed AlnumayNorah A. AlzahraniNouf M. AlotaibiHisham Abdullah AlyahyaSultan AlrashedFaisal MirzaShaykhah AlsubaieHassan A. AlahmedGhadah AlabduljabbarRaghad AlkhathranYousef AlmushayqihRaneem AlnajimSalman AlsubaihiMaryam Al MansourMajed AlrubaianAli AlammariZaki AlawamiAbdulmohsen Al-ThubaityAhmed AbdelaliJeril KuriakoseAbdalghani AbujabalNora Al-TwaireshAreeb AlowisheqHaidar KhanPublished in: CoRR (2024)
Keyphrases
- language model
- arabic language
- language identification
- cross language retrieval
- language modeling
- statistical machine translation
- arabic documents
- probabilistic model
- document retrieval
- document level
- n gram
- cross lingual
- information retrieval
- speech recognition
- retrieval model
- cross language
- query expansion
- multiword
- test collection
- smoothing methods
- machine translation
- relevance model
- natural language
- language models for information retrieval
- vector space model
- language modelling
- ad hoc information retrieval
- cross language information retrieval
- context sensitive
- query terms
- query translation
- spoken term detection
- out of vocabulary
- term dependencies
- translation model
- handwriting recognition
- language independent
- web search
- bayesian networks