Category: Meetings

Samuele D’Avenia will talk about one of his recent works, the abstract of which is reported below.

Several recent works have examined the generations produced by large language models (LLMs) on subjective topics such as political opinions and attitudinal questionnaires, with a particular interest in controlling these outputs to align with specific users or perspectives.

This work investigates how irrelevant contextual information can systematically influence the outputs of Large Language Models (LLMs) when generating opinions on subjective topics. Using the Political Compass Test as a case study, we analyze LLM-generated responses in an open-generation setting and conduct a detailed statistical analysis to quantify shifts in opinions caused by unrelated contextual cues. Our findings reveal that some of these elements can predictably bias model responses, further highlighting challenges in ensuring the robustness and reliability of LLMs when generating opinions on subjective topics

When:  4/07/2025, h 11.30

Where:  Sala conferenze – 3rd floor

Eliana Di Palma will explore the connection between language and emotions, focusing on how words can convey emotions. A central topic will be ELIta, an Italian emotion lexicon containing over 6,000 words and emojis, manually annotated by native speakers. This resource is designed to support the analysis of emotional content in various types of texts, including both formal writing and everyday communication, such as messages and social media. Practical examples will illustrate how words are linked to emotions, and how these associations may vary depending on factors such as age, gender, and cultural background. The talk will conclude with a study on oxymorons, examining the relationship between their components and their emotional perception from both psycholinguistic and computational perspectives.

When:  6/06/2025, h 11.30

Where:  Sala Seminari – 1st floor

CCC Seminar by Anna Koufakou, visiting professor from Florida Gulf University, United States

Abstract

The evolution of Natural Language Processing (NLP) technologies, with the advent of Large Language Models (LLMs) and Generative AI, has significantly expanded the scope and effectiveness of NLP-driven tools across applications. Among these, Automated Emotion Recognition (AER) represents a particularly challenging yet promising area of research. Unlike Sentiment Analysis, which usually categorizes sentiment as positive or negative, AER aims to identify specific emotional states, such as anger, joy, or sadness, that can vary widely in expression and meaning. This talk explores the current landscape of relevant text corpora and resources, including our recent efforts towards a unifying benchmark. We will also discuss recent practices and key challenges in this evolving field.

When:  29/05/2025, h 10.00

Where:  Sala Conferenze – 3rd floor

Michael Oliverio will talk about one of his work entitled ‘WebNLG-IT: Construction of an aligned RDF-Italian corpus throughMachine Translation techniques’

Abstract

The main goal of this work is the creation of the Italian version of the WebNLG corpus through the application of Neural Machine Translation (NMT) and post-editing with hand-written rules. To achieve this goal, in a first step, several existing NMT models were analysed and compared in order to identify the system with the highest performance on the original corpus. In a second step, after using the best NMT system, we semi-automatically designed and applied a number of rules to refine and improve the quality of the produced resource, creating a new corpus named WebNLG-IT. We used this resource for fine-tuning several LLMs for RDF-to-text tasks. In this way, comparing the performance of LLM-based generators on both Italian and English, we have (1) evaluated the quality of WebNLG-IT with respect to the original English version, (2) released the first fine-tuned LLM-based system for generating Italian from semantic web triples and (3) introduced an Italian version of a modular generation pipeline for RDF-to-text.

When:  11/04/2025, h 11.30

Where:  Sala Conferenze – 3rd floor

Manuela Sanguinetti will hold a seminar titled “Computational Linguistics in Action: From Text Corpora to Real-World Challenges.”

Bio

Manuela Sanguinetti received her Ph.D. in Computer Science from the University of Turin in 2016. She is currently a non-tenured assistant professor at the Department of Mathematics and Computer Science, University of Cagliari, where she has been working on a project funded by the National Reform and Resilience Plan (PNRR).
Her work primarily focuses on the development of linguistic resources to enhance language understanding and processing. She has been involved in a wide range of research collaborations regarding the study of task-oriented conversational agents, hate speech and stereotype detection, and multilingualism.

When:  03/04/2025, h 16.00

Where: Sala Riunioni – 1st floor

Online link: https://meet.google.com/ztd-mjgc-yjv

Alan Ramponi will talk about one of his projects entitled “NLP meets non-standard languages: Opportunities and ethical responsibilities”.

Abstract

After many years of research focused primarily on standardized languages, the natural language processing (NLP) community has recently begun to include “non-standard” language varieties in its repertoire. This opens new opportunities for research, but it also presents unprecedented challenges and calls for greater ethical responsibilities. In this seminar, I will present recent work in NLP for non-standard languages with a focus on language varieties of Italy, highlighting i) the importance of accounting for linguistic variation and how to explore it, ii) the problematic assumption of considering all language varieties as the same in terms of language functions and technological needs, and iii) the need to actively engage with speech communities when dealing with endangered languages to co-design locally-meaningful artifacts that meet their needs and represent their language varieties.

Bio

Alan Ramponi is a senior researcher in natural language processing (NLP) at Fondazione Bruno Kessler, Italy, where he is part of the Digital Humanities research group. His research focuses on language variation across many dimensions (e.g., non-standard varieties and dialects, domains, registers, social factors). He is interested in how NLP can contribute to the study of language variation, and how accounting for language variation can contribute to more robust, fair, and inclusive NLP. Web page: https://alanramponi.github.io/

When:  28/03/2025, h 11.00

Where: Aula 3.06 Thin Client (terzo piano) – Via Sant’Ottavio ,54

Online link: https://meet.google.com/gvw-dfuo-bvt 

Beatrice Savoldi will present one of her recent work
entitle “Hi Guys or Hi folks? Navigating Gender Bias and Inclusive Language in Translation Technologies”.

Abstract

Societal gender asymmetries and inequalities can be embedded in our communication practices and perpetuated in language technologies, including Machine Translation (MT) systems used as scale. In this presentation, we will delve into the current landscape of MT and gender bias, as well as current proposals towards more inclusive language. 

By focusing on English-Italian as an exemplar language pair, we will discuss the challenges and opportunities — both theoretical, technical but also linguistic —  in fostering a more equitable automatic translation. 

When: 14/03/2025 11.00

Where: Aula 3.06 Thin Client (terzo piano) – Via Sant’Ottavio 54

Horacio Jarquin will present one of his projects
entitle “GAttention: Gated Attention for the Detection of Abusive Language”.

Abstract

Abusive language online creates toxic environments and exacerbates social tensions, underscoring the need for robust NLP models to interpret nuanced linguistic cues. This research introduces GAttention, a novel Gated Attention mechanism that combines the strengths of Contextual attention and Self-attention mechanisms to address the limitations of existing attention models within the text classification task. GAttention capitalizes on local and global query vectors by integrating the internal relationships within a sequence (Self-attention) and the global relationships among distinct sequences (Contextual attention). This combination allows for a more nuanced understanding and processing of sequence elements, which is particularly beneficial in context-sensitive text classification tasks such as the case of abusive language detection. By applying this mechanism to transformer-based encoder models, we showcase how it enhances the model’s ability to discern subtle nuances and contextual clues essential for identifying abusive language, a challenging and increasingly relevant task within NLP.

When: 21/03/2025 11.30

Where: Sala Riunioni (first floor)

Adriana Pagano will present one of her international projects
entitle “Bridging views on the concepts of ‘multilingual’, ‘cross-lingual’ and ‘translingual’ in Language Technology”.

Abstract

The presentation will introduce the interdisciplinary research network UniDive (Universality, Diversity, and Idiosyncrasy in Language Technology), a COST Action (European Cooperation in Science and Technology). Adriana will focus on one of the tasks she is currently leading within UniDive’s Working Group 3 – Multilingual and Cross-Lingual Language Technology.

When: 17/01/2025 11.30

Where: Sala Conferenze (3rd floor)

Marco Madeddu is a PhD student at the beginning of her 1st year, and he will talk about one of his latest works called “Exploring YouTube Comments Reacting to Femicide News in Italian”

Abstract

In recent years, the Gender Based Violence (GBV) has become an important issue in modern society and a central topic in different research areas due to its alarming spread.
Several Natural Language Processing (NLP) studies, concerning Hate Speech directed against women, have focused on misogynistic behaviours, slurs or incel communities.
The main contribution of our work is the creation of the first dataset on social media comments to GBV, in particular to a femicide event.
Our dataset, named GBV-Maltesi, contains 2,934 YouTube comments annotated following a new schema that we developed in order to study GBV and misogyny with an intersectional approach.
During the experimental phase, we trained models on different corpora for binary misogyny detection and found that datasets that mostly include explicit expressions of misogyny are an easier challenge, compared to more implicit forms of misogyny contained in GBV-Maltesi.

When: 13/12/2024 11.30

Where: Sala Conferenze (3rd floor)