Back to Search
Start Over
CBAG: Conditional biomedical abstract generation
- Source :
- PLoS ONE, PLoS ONE, Vol 16, Iss 7, p e0253905 (2021)
- Publication Year :
- 2021
- Publisher :
- Public Library of Science, 2021.
-
Abstract
- Biomedical research papers use significantly different language and jargon when compared to typical English text, which reduces the utility of pre-trained NLP models in this domain. Meanwhile Medline, a database of biomedical abstracts, introduces nearly a million new documents per-year. Applications that could benefit from understanding this wealth of publicly available information, such as scientific writing assistants, chat-bots, or descriptive hypothesis generation systems, require new domain-centered approaches. A conditional language model, one that learns the probability of words given some a priori criteria, is a fundamental building block in many such applications. We propose a transformer-based conditional language model with a shallow encoder "condition" stack, and a deep "language model" stack of multi-headed attention blocks. The condition stack encodes metadata used to alter the output probability distribution of the language model stack. We sample this distribution in order to generate biomedical abstracts given only a proposed title, an intended publication year, and a set of keywords. Using typical natural language generation metrics, we demonstrate that this proposed approach is more capable of producing non-trivial relevant entities within the abstract body than the 1.5B parameter GPT-2 language model.
- Subjects :
- FOS: Computer and information sciences
Computer Science - Machine Learning
Biomedical Research
Computer science
Cancer Treatment
Social Sciences
02 engineering and technology
Machine Learning (cs.LG)
Statistics - Machine Learning
0202 electrical engineering, electronic engineering, information engineering
Medicine and Health Sciences
Psychology
Nanotechnology
Data Mining
Language
0303 health sciences
Multidisciplinary
Publications
Software Engineering
Nanopatterning
Surgical Oncology
Oncology
Physical Sciences
Medicine
Engineering and Technology
Encoder
Research Article
Clinical Oncology
Computer and Information Sciences
Science
MEDLINE
Pain
Machine Learning (stat.ML)
Context (language use)
Surgical and Invasive Medical Procedures
ENCODE
Set (abstract data type)
03 medical and health sciences
Signs and Symptoms
Scientific writing
020204 information systems
Humans
030304 developmental biology
Transformer (machine learning model)
Information retrieval
Cognitive Psychology
Biology and Life Sciences
Myalgia
Probability Theory
Probability Distribution
Medical Writing
Metadata
Cognitive Science
Laparoscopy
Programming Languages
Language model
Clinical Medicine
Mathematics
Neuroscience
Subjects
Details
- Language :
- English
- ISSN :
- 19326203
- Volume :
- 16
- Issue :
- 7
- Database :
- OpenAIRE
- Journal :
- PLoS ONE
- Accession number :
- edsair.doi.dedup.....c8ac5cb390d872199063f7dbe08e890e