Héctor Allende-Cid — accepted AI-conference papers

2025

PM3-KIE: A Probabilistic Multi-Task Meta-Model for Document Key Information Extraction

Birgit Kirsch, Héctor Allende-Cid, Stefan Rueping

ACL 2025finding

Key Information Extraction (KIE) from visually rich documents is commonly approached as either fine-grained token classification or coarse-grained entity extraction. While token-level models capture spatial and visual cues, entity-level models better represent logical dependencies and align with rea…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

Robustness Evaluation of the German Extractive Question Answering Task

Shalaka Satheesh, Katharina Beckh, Katrin Klug, Héctor Allende-Cid, Sebastian Houben, Teena Hassan

COLING 2025main

To ensure reliable performance of Question Answering (QA) systems, evaluation of robustness is crucial. Common evaluation benchmarks commonly only include performance metrics, such as Exact Match (EM) and the F1 score. However, these benchmarks overlook critical factors for the deployment of QA syst…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗