Papers by Giuseppe Sartori

2 papers
ZeroNER: Fueling Zero-Shot Named Entity Recognition via Entity Type Descriptions (2025.findings-acl)

Copied to clipboard

Challenge: Existing zero-shot learning methods rely on entity type names for generalization . current solutions require large datasets and prioritize a handful of commonly occurring types .
Approach: They propose a description-driven framework that enhances hard zero-shot NER in low-resource settings.
Outcome: The proposed framework outperforms existing models by up to 16% in the F1 score . it also surpasses baseline models that use type names alone .
DecOp: A Multilingual and Multi-domain Corpus For Detecting Deception In Typed Text (2020.lrec-1)

Copied to clipboard

Challenge: Recent studies show that humans are ineffective in spotting deceit, with accuracy rates only slightly above the chance level.
Approach: They propose a new language resource for automatic deception detection in cross-domain and cross-language scenarios.
Outcome: The proposed language resource is composed of 5000 examples of truthful and deceitful first-person opinions across five different domains and two languages.

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