AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Multi-Task Medical Concept Normalization Using Multi-View Convolutional Neural Network

Yi Luo, Guojie Song, Pengyu Li, Zhongang Qi

AAAI 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Uncertainty-aware multi-view learning · 28 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add multi-task shared structure (single-task to multi-task) (ablation)MTMV-CNN · Disease normalizationaccuracy: 83.61 -> 85.59Improved
add multi-task shared structure (single-task to multi-task) (ablation)MTMV-CNN · Procedure normalizationaccuracy: 90.75 -> 91.69Improved
add sentence view to string+char+word views (ablation)MTMV-CNN · Procedure normalizationaccuracy: 87.83 -> 91.69Improved
add sentence view to string+char+word views (ablation)MTMV-CNN · Disease normalizationaccuracy: 85.00 -> 85.59Improved
use four views instead of char view only (ablation)MTMV-CNN · Disease normalizationaccuracy: 82.99 -> 85.59Improved
use four views instead of best single view (sentence) (ablation)MTMV-CNN · Procedure normalizationaccuracy: 90.17 -> 91.69Improved
use word view alone instead of other single views (ablation)MTMV-CNN · Disease normalizationaccuracy: 75.76 vs 82.99 (char)Hurt
vary co-occurrence constraint weight lambda from 0.001 to 100 (ablation)MTMV-CNN · Disease and procedure normalizationF1Mixed
replace matching matrix CNN (MatchPyramid) with matching tensor and multi-view CNNMatchPyramid · Disease normalizationaccuracy: 80.16 -> 85.59Improved
replace matching matrix CNN (MatchPyramid) with matching tensor and multi-view CNNMatchPyramid · Procedure normalizationaccuracy: 83.51 -> 91.69Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy