Lessons Learned from GPT-SW3: Building the First Large-Scale Generative Language Model for Swedish.
Ariel EkgrenAmaru Cuba GyllenstenEvangelia GogoulouAlice HeimanSeverine VerlindenJoey ÖhmanFredrik CarlssonMagnus SahlgrenPublished in: LREC (2022)
Keyphrases
- lessons learned
- language model
- language modeling
- probabilistic model
- document retrieval
- n gram
- speech recognition
- case study
- language modelling
- information retrieval
- generative model
- query expansion
- ad hoc information retrieval
- test collection
- retrieval model
- context sensitive
- language modeling framework
- statistical language models
- mixture model
- language model for information retrieval
- document ranking
- relevance model
- translation model
- smoothing methods
- real world
- pseudo relevance feedback
- vector space model
- query terms
- statistical machine translation
- word error rate
- unsupervised learning
- co occurrence
- search engine