Structured information extraction from complex scientific text with fine-tuned large language models.
Alexander DunnJohn DagdelenNicholas WalkerSanghoon LeeAndrew S. RosenGerbrand CederKristin A. PerssonAnubhav JainPublished in: CoRR (2022)
Keyphrases
- language model
- information extraction
- information retrieval
- language modeling
- fine tuned
- text mining
- textual data
- free text
- n gram
- speech recognition
- probabilistic model
- document retrieval
- structured data
- language modelling
- document level
- natural language text
- text documents
- query expansion
- smoothing methods
- test collection
- natural language processing
- statistical language models
- retrieval model
- multiword
- web documents
- question answering
- ad hoc information retrieval
- context sensitive
- co occurrence
- keywords
- okapi bm
- language model for information retrieval
- machine learning
- translation model
- passage retrieval
- fine tuning
- text retrieval
- query terms
- relevant documents
- retrieval systems
- relevance model
- pseudo relevance feedback
- text summarization
- query specific
- named entity recognition
- semi structured
- language models for information retrieval
- general purpose