Detecting out-of-distribution text using topological features of transformer-based language models.
Andres PollanoAnupam ChaudhuriAnj SimmonsPublished in: CoRR (2023)
Keyphrases
- language model
- topological features
- information retrieval
- language modeling
- n gram
- document retrieval
- speech recognition
- statistical language models
- document level
- retrieval model
- probabilistic model
- language modelling
- multiword
- text retrieval
- query expansion
- link prediction
- persistent homology
- test collection
- text mining
- query terms
- vector space model
- context sensitive
- smoothing methods
- relevance model
- language models for information retrieval
- spoken term detection
- translation model
- sentence level
- document ranking
- pseudo relevance feedback
- tf idf
- text documents
- keywords