Papers by Birgit Kirsch

1 papers
PM3-KIE: A Probabilistic Multi-Task Meta-Model for Document Key Information Extraction (2025.findings-acl)

Copied to clipboard

Challenge: a probabilistic multi-task meta-model for key information extraction is proposed . entity-level models capture spatial and visual cues, while fine-grained token classification models capture logical dependencies.
Approach: They propose a probabilistic multi-task meta-model that integrates fine-grained token classification and coarse-grain entity extraction models.
Outcome: The proposed model outperforms state-of-the-art models and a stacked ensemble on two datasets.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations