Labeling Clinical Reports with Active Learning and Topic Modeling

Labeling Clinical Reports with Active Learning and Topic Modeling

Supervised machine learning models require a labeled data set of high quality in order to perform well. Available text data often exists in abundance, but it is usually not labeled. Labeling text data is a time consuming process, especially in the case where multiple labels can be assigned to a sing...

Full description

Bibliographic Details
Main Author: Lindblad, Simon
Format: Others
Language:English
Published: Linköpings universitet, Interaktiva och kognitiva system 2018
Subjects:
active learning
topic modeling
topic models
Maximum Loss Reduction with Maximum Confidence
Binary Version Space Minimization
Clinical Reports
Computer Sciences
Datavetenskap (datalogi)
Online Access:http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-148463

Internet

http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-148463

Similar Items