Back to Search
Start Over
SpanPredict: Extraction of Predictive Document Spans with Neural Attention
- Source :
- NAACL-HLT
- Publication Year :
- 2021
- Publisher :
- Association for Computational Linguistics, 2021.
-
Abstract
- In many natural language processing applications, identifying predictive text can be as important as the predictions themselves. When predicting medical diagnoses, for example, identifying predictive content in clinical notes not only enhances interpretability, but also allows unknown, descriptive (i.e., text-based) risk factors to be identified. We here formalize this problem as predictive extraction and address it using a simple mechanism based on linear attention. Our method preserves differentiability, allowing scalable inference via stochastic gradient descent. Further, the model decomposes predictions into a sum of contributions of distinct text spans. Importantly, we require only document labels, not ground-truth spans. Results show that our model identifies semantically-cohesive spans and assigns them scores that agree with human ratings, while preserving classification performance.
- Subjects :
- Computer science
business.industry
Mechanism based
Inference
02 engineering and technology
010501 environmental sciences
Machine learning
computer.software_genre
01 natural sciences
Stochastic gradient descent
Simple (abstract algebra)
Scalability
0202 electrical engineering, electronic engineering, information engineering
020201 artificial intelligence & image processing
Artificial intelligence
Medical diagnosis
business
computer
Predictive text
0105 earth and related environmental sciences
Interpretability
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Accession number :
- edsair.doi...........ad2d821c9e08195eadcb9a3b17f77557