AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Extracting PICO Sentences from Clinical Trial Reports using Supervised Distant Supervision

Byron C. Wallace, Joël Kuiper, Aakash Sharma, Mingxi (Brian) Zhu, Iain J. Marshall

JMLR 2016 · Label-efficient and robust learning › Semi-supervised learning · approach: Self-training theory · 134 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
replace direct-only training with SDS (add distant supervision filtered by learned mapping)Direct only · PICO Population (retrospective)Mean AUC: 0.904 -> 0.947Improved
replace direct-only training with SDSDirect only · PICO Outcomes (retrospective)Mean AUC: 0.837 -> 0.900Improved
add SDS filtering of candidate sentences to plain distant supervisionDS · PICO Population (retrospective)Mean AUC: 0.941 -> 0.947Improved
add SDS filtering to plain distant supervisionDS · PICO Interventions (retrospective)Precision@20: 0.172 -> 0.172No clear effect
add SDS filtering to plain distant supervisionDS · PICO Population (retrospective)Precision@10: 0.202 -> 0.212Improved
add SDS filtering to plain distant supervisionDS · PICO Population (retrospective)Mean NDCG@20: 0.484 -> 0.548Improved
use SDS instead of Nguyen pooling of direct and distant modelsNguyen · PICO Population (retrospective)Mean AUC: 0.917 -> 0.947Improved
use SDS instead of Nguyen poolingNguyen · PICO Interventions (retrospective)Precision@3: 0.419 -> 0.389Hurt
use SDS instead of Nguyen poolingNguyen · PICO Outcomes (retrospective)Mean NDCG@20: 0.339 -> 0.333Hurt
use SDS instead of Nguyen poolingNguyen · PICO Interventions (prospective)Precision@3: 0.854 -> 0.903Improved
use SDS instead of Nguyen poolingNguyen · PICO Population (prospective)Precision@3: 0.907 -> 0.927Improved
use SDS instead of Nguyen poolingNguyen · PICO Outcomes (prospective)Precision@3: 0.880 -> 0.887Improved

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