AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Exploiting a Zoo of Checkpoints for Unseen Tasks

Jiaji Huang, Qiang Qiu, Kenneth Church

NeurIPS 2021 · Probabilistic and scientific modeling › Molecules and proteins · approach: Neuro-symbolic probabilistic layers · 0 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
Select five checkpoints using MMI instead of the bert-large-cased best layerCheckpoint feature selection · CoNLL2000 Chunkingscore: 93.64 -> 93.88Improved
Select five checkpoints using MMI instead of the bert-large-cased best layerCheckpoint feature selection · CoNLL2003 NERscore: 84.44 -> 88.64Improved
Select five checkpoints using MMI instead of the bert-large-cased best layerCheckpoint feature selection · PTB POSscore: 96.73 -> 97.57Improved
Select five checkpoints using MMI instead of the bert-large-cased best layerCheckpoint feature selection · Semantic Taggingscore: 93.83 -> 94.35Improved
Select five checkpoints using MMI instead of the bert-large-cased best layerCheckpoint feature selection · ItHappened-v2 Event FactualityPearson correlation: 76.25 -> 78.35Improved
Select five checkpoints using MMI instead of the bert-large-cased best layerCheckpoint feature selection · PTB Parent taggingscore: 96.10 -> 96.64Improved
Select five checkpoints using MMI instead of the bert-large-cased best layerCheckpoint feature selection · PTB Gparent taggingscore: 82.46 -> 85.85Improved
Select five checkpoints using MMI instead of the bert-large-cased best layerCheckpoint feature selection · PTB GGparent taggingscore: 67.90 -> 73.32Improved
Select checkpoints with MMI rather than randomlyCheckpoint feature selection · CIFAR100 unseen 30-way tasksaverage validation accuracyImproved
Choose checkpoints based on the first unseen task rather than MMI selectionCheckpoint feature selection · CIFAR100 unseen 30-way tasksaverage validation accuracyMixed

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