AI Paper Atlas

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

Learning Pipelines with Limited Data and Domain Knowledge: A Study in Parsing Physics Problems

Mrinmaya Sachan, Kumar Avinava Dubey, Tom M. Mitchell, Dan Roth, Eric P Xing

NeurIPS 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 20 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
learn the pipeline jointly with trust model instead of traditional pipeline with AdaBoost combination (ablation)Nuts&Bolts · Physics diagram parsingF1: 0.66 -> 0.74Improved
add trust modelling of function approximators (ablation)Nuts&Bolts · Physics diagram parsingF1: 0.64 -> 0.74Improved
learn rule weights instead of fixing them to 1 (ablation)Nuts&Bolts · Physics diagram parsingF1: 0.59 -> 0.74Improved
add all unlabelled diagrams to semi-supervised training (ablation)Nuts&Bolts · Physics diagram parsingF1: 0.58 -> 0.74Improved
reduce text-element supervision from 207 to 25 diagrams (ablation)Nuts&Bolts · Physics diagram parsingF1: 0.74 -> 0.61Hurt
Nuts&Bolts diagram parser instead of EdgeBoxes/G-ALIGNER/DSDP-Net baselinesNuts&Bolts · Physics diagram parsingF1: 0.65 -> 0.74Improved
use Nuts&Bolts diagram parses in question answeringParsing to Programs solver · Textbook physics QAaccuracy: 23 -> 32Improved
Nuts&Bolts instead of Snorkel for relation extractionNuts&Bolts · CDR relation extractionF1: 45.3 -> 47.1Improved
Nuts&Bolts instead of Snorkel for relation extractionNuts&Bolts · Genomics relation extractionF1: 57.2 -> 57.3No clear effect
Nuts&Bolts semi-supervised instead of semi-supervised PCFGNuts&Bolts · Physics diagram parsingF1: 0.58 -> 0.74Improved

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