AI Paper Atlas

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

Joint Inference over a Lightly Supervised Information Extraction Pipeline: Towards Event Coreference Resolution for Resource-Scarce Languages

Chen Chen, Vincent Ng

AAAI 2016 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 23 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
apply ILP joint inference over IE pipeline outputs (ablation)Lightly supervised event coreference resolver · ACE 2005 ChineseCoNLL F1: 38.7 -> 40.7Improved
apply ILP joint inference (ablation)Lightly supervised resolver · ACE 2005 ChineseMUC F1: 39.2 -> 41.5Improved
apply ILP joint inference (ablation)Lightly supervised resolver · ACE 2005 ChineseBLANC F1: 23.2 -> 24.9Improved
coreference-aware active learning instead of random sentence selection (ablation)Event coreference resolver · ACE 2005 Chinese, 2,000 sentencesCoNLL F1: 32.0% -> 38.7%Improved
lightly supervised pipeline with ILP vs fully supervised SinoCoreferencerSinoCoreferencer · ACE 2005 ChineseCoNLL F1: 39.2 -> 40.7Improved

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