Italian Event Detection Goes Deep Learning

TL;DR

This paper explores the use of various word embeddings to enhance a Bi-LSTM-CRF model for Italian event detection, achieving state-of-the-art results and emphasizing the importance of embeddings.

Contribution

It introduces a single-step approach using different embeddings that significantly improves event detection and classification in Italian, setting new performance benchmarks.

Findings

F1 score for detection improved by 1.3 points

F1 score for classification improved by 6.5 points

Embeddings have a major impact on model performance

Abstract

This paper reports on a set of experiments with different word embeddings to initialize a state-of-the-art Bi-LSTM-CRF network for event detection and classification in Italian, following the EVENTI evaluation exercise. The net- work obtains a new state-of-the-art result by improving the F1 score for detection of 1.3 points, and of 6.5 points for classification, by using a single step approach. The results also provide further evidence that embeddings have a major impact on the performance of such architectures.