Evaluating the Impact of Text Duplications on a Corpus of More than 600, 000 Clinical Narratives in a French Hospital.
William DiganMaxime WackVincent LootenAntoine NeurazAnita BurgunBastien RancePublished in: MedInfo (2019)
Keyphrases
- supervised machine learning
- broad coverage
- patient records
- diagnostic imaging
- open domain
- text data
- free text
- plain text
- sentence level
- health care
- natural language text
- patient care
- text corpora
- clinical information
- newspaper articles
- information retrieval
- mono lingual
- text corpus
- lexical features
- recognizing textual entailment
- multiword
- english words
- named entity disambiguation
- intensive care
- text retrieval
- document corpus
- home care
- text documents
- cross lingual
- medical practice
- natural language processing
- intensive care unit
- clinical decision support systems
- patient data
- scientific papers
- clinical practice
- document level
- world knowledge
- linguistic patterns
- training corpus
- word pairs
- information extraction
- keywords
- health related
- topic segmentation
- spontaneous speech
- anaphora resolution
- relation extraction
- medical doctors
- information systems