Unsupervised Subtitle Segmentation with Masked Language Models.
David PonceThierry EtchegoyhenVictor Ruiz GómezPublished in: ACL (2) (2023)
Keyphrases
- language model
- language modeling
- probabilistic model
- n gram
- information retrieval
- retrieval model
- document retrieval
- language modelling
- query expansion
- fully unsupervised
- ad hoc information retrieval
- speech recognition
- image segmentation
- statistical language models
- context sensitive
- smoothing methods
- test collection
- language model for information retrieval
- word segmentation
- query terms
- document ranking
- vector space model
- pseudo relevance feedback
- term dependencies
- language models for information retrieval
- active learning