AI Paper Atlas

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

Understanding Medical Conversations with Scattered Keyword Attention and Weak Supervision from Responses

Xiaoming Shi, Haifeng Hu, Wanxiang Che, Zhongqian Sun, Ting Liu, Junzhou Huang

AAAI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 30 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 label-embedding attention (ablation)TextCNN · Medical slot filling testMicro F1: 70.69 -> 73.07Improved
add label-embedding attention (ablation)Star-Transformer · Medical slot filling testMicro F1: 74.04 -> 76.90Improved
add label-embedding attention (ablation)DRNN · Medical slot filling testMicro F1: 74.83 -> 76.07Improved
add label-embedding attention (ablation)TextCNN · Medical slot filling testMacro F1: 56.95 -> 62.40Improved
add weak supervision pre-training on top of attention (ablation)TextCNN+A · Medical slot filling testMicro F1: 73.07 -> 78.76Improved
add weak supervision pre-training on top of attention (ablation)DRNN+A · Medical slot filling testMicro F1: 76.07 -> 81.15Improved
add weak supervision pre-training on top of attention (ablation)Star-Transformer+A · Medical slot filling testTurn accuracy: 53.20 -> 52.80Hurt
add weak supervision pre-training on top of attention (ablation)Star-Transformer+A · Medical slot filling testMicro F1: 76.90 -> 78.05Improved
add weak supervision pre-training on top of BERT features (ablation)TextCNN+B · Medical slot filling testMicro F1: 71.22 -> 75.56Improved
add BERT fixed features (ablation)TextCNN · Medical slot filling testMicro F1: 70.69 -> 71.22Improved
use response concepts instead of query concepts as weak supervision (ablation)TextCNN+WS · Medical slot filling testMicro F1: 53.64 -> 72.59Improved
use response concepts instead of query concepts as weak supervision (ablation)TextCNN+WS · Medical slot filling testTurn accuracy: 27.50 -> 53.30Improved

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