Cesare Campagnano

Hi!

I’m a third-year PhD student at Sapienza University of Rome. I’m an ex Applied Scientist II Intern at Amazon. My main research focuses on Large Language Models and Sentiment Analysis.

I don’t remember a day in which I was not passionate about computer science and, even more, all its implications. My interests have ranged from programming to graphics, through web development, even video editing, finally leading to artificial intelligence. I assure that this is my final interest… Well, maybe!

I like to teach machines how to understand human language. The core idea is to help people in their work and create new opportunities.

news

Oct 17, 2022	Starting a position as Applied Scientist Intern at Amazon, in Barcelona!
Mar 15, 2022	Long paper accepted at ACL 2022: “SRL4E - Semantic Role Labeling for Emotions: A Unified Evaluation Framework”. See you in Dublin!
Mar 1, 2021	This year I will be TA for the Natural Language Processing class at Computer Science Dept.
Nov 1, 2020	Starting a Ph.D. in Natural Language Processing + Deep Learning at Sapienza University of Rome!

selected publications

ACL

SRL4E – Semantic Role Labeling for Emotions: A Unified Evaluation Framework

Campagnano, Cesare, Conia, Simone, and Navigli, Roberto

In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) May 2022

Abs PDF Code

In the field of sentiment analysis, several studies have highlighted that a single sentence may express multiple, sometimes contrasting, sentiments and emotions, each with its own experiencer, target and/or cause. To this end, over the past few years researchers have started to collect and annotate data manually, in order to investigate the capabilities of automatic systems not only to distinguish between emotions, but also to capture their semantic constituents. However, currently available gold datasets are heterogeneous in size, domain, format, splits, emotion categories and role labels, making comparisons across different works difficult and hampering progress in the area. In this paper, we tackle this issue and present a unified evaluation framework focused on Semantic Role Labeling for Emotions (SRL4E), in which we unify several datasets tagged with emotions and semantic roles by using a common labeling scheme. We use SRL4E as a benchmark to evaluate how modern pretrained language models perform and analyze where we currently stand in this task, hoping to provide the tools to facilitate studies in this complex area.