EventNet-ITA: Italian Frame Parsing for Events

TL;DR

EventNet-ITA is a comprehensive Italian event frame corpus with an efficient parsing model, enabling advanced research and applications in Italian event understanding.

Contribution

The paper introduces the first large-scale Italian event frame corpus and an effective multi-label sequence labeling approach for frame parsing.

Findings

Achieved 0.9 strict F1-score for frame classification.

Achieved 0.72 F1-score for frame element classification.

Corpus and model are publicly available under open license.

Abstract

This paper introduces EventNet-ITA, a large, multi-domain corpus annotated full-text with event frames for Italian. Moreover, we present and thoroughly evaluate an efficient multi-label sequence labeling approach for Frame Parsing. Covering a wide range of individual, social and historical phenomena, with more than 53,000 annotated sentences and over 200 modeled frames, EventNet-ITA constitutes the first systematic attempt to provide the Italian language with a publicly available resource for Frame Parsing of events, useful for a broad spectrum of research and application tasks. Our approach achieves a promising 0.9 strict F1-score for frame classification and 0.72 for frame element classification, on top of minimizing computational requirements. The annotated corpus and the frame parsing model are released under open license.