atlas

Research map / Learning theory and algorithms / Combinatorial and search optimization

Discovering Interpretable Data-to-Sequence Generators

AAAI 2022 · Learning theory and algorithms › Combinatorial and search optimization · approach: Constrained neural network optimization · 3 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Use CONSEQUENCE instead of DATSEvent-sequence prediction · ProductionNLS: 0.35 -> 0.42Helped
Use CONSEQUENCE instead of LSTMEvent-sequence prediction · SepsisNLS: 0.51 -> 0.58Helped
Use CONSEQUENCE instead of LSTMEvent-sequence prediction · Rolling MillNLS: 0.99 -> 0.94Hurt
Use CONSEQUENCE instead of POSCLEvent-sequence prediction · SoftwareNLS: 0.69 -> 0.84Helped
Replace GERD with CANTMINERPB for rule learning (ablation)CONSEQUENCE on synthetic data · Synthetic data with varying numbers of attributesTraining timeHurt
Replace GERD with CLASSY for rule learning (ablation)CONSEQUENCE on synthetic data · Synthetic data with varying numbers of attributesNumber of condition termsHurt
Train on larger subsets of Rolling Mill dataCONSEQUENCE · Rolling MillNLSNo clear effect

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