Search Results for author: Sara Tonelli

Found 51 papers, 12 papers with code

Features or Spurious Artifacts? Data-centric Baselines for Fair and Robust Hate Speech Detection

1 code implementation NAACL 2022 Alan Ramponi, Sara Tonelli

Avoiding to rely on dataset artifacts to predict hate speech is at the cornerstone of robust and fair hate speech detection.

Fairness Hate Speech Detection

Are Gestures Worth a Thousand Words? An Analysis of Interviews in the Political Domain

no code implementations ACL (mmsr, IWCS) 2021 Daniela Trotta, Sara Tonelli

Speaker gestures are semantically co-expressive with speech and serve different pragmatic functions to accompany oral modality.

Retrieval

Challenges in Designing Games with a Purpose for Abusive Language Annotation

no code implementations EACL (HCINLP) 2021 Federico Bonetti, Sara Tonelli

In this paper we discuss several challenges related to the development of a 3D game, whose goal is to raise awareness on cyberbullying while collecting linguistic annotation on offensive language.

Abusive Language

Fine-Grained Fairness Analysis of Abusive Language Detection Systems with CheckList

1 code implementation ACL (WOAH) 2021 Marta Marchiori Manerba, Sara Tonelli

Our evaluation shows that, although BERT-based classifiers achieve high accuracy levels on a variety of natural language processing tasks, they perform very poorly as regards fairness and bias, in particular on samples involving implicit stereotypes, expressions of hate towards minorities and protected attributes such as race or sexual orientation.

Abusive Language Fairness

FrameNet-like Annotation of Olfactory Information in Texts

no code implementations EMNLP (LaTeCHCLfL, CLFL, LaTeCH) 2021 Sara Tonelli, Stefano Menini

Although olfactory references play a crucial role in our cultural memory, only few works in NLP have tried to capture them from a computational perspective.

Natural Language Understanding

Building a Multilingual Taxonomy of Olfactory Terms with Timestamps

no code implementations LREC 2022 Stefano Menini, Teresa Paccosi, Serra Sinem Tekiroğlu, Sara Tonelli

Olfactory references play a crucial role in our memory and, more generally, in our experiences, since researchers have shown that smell is the sense that is most directly connected with emotions.

Agreeing to Disagree: Annotating Offensive Language Datasets with Annotators’ Disagreement

1 code implementation EMNLP 2021 Elisa Leonardelli, Stefano Menini, Alessio Palmero Aprosio, Marco Guerini, Sara Tonelli

Since state-of-the-art approaches to offensive language detection rely on supervised learning, it is crucial to quickly adapt them to the continuously evolving scenario of social media.

BERToldo, the Historical BERT for Italian

1 code implementation LT4HALA (LREC) 2022 Alessio Palmero Aprosio, Stefano Menini, Sara Tonelli

This has led to the creation of BERT-like models for different languages trained with digital repositories from the past.

POS POS Tagging

Work Hard, Play Hard: Collecting Acceptability Annotations through a 3D Game

1 code implementation LREC 2022 Federico Bonetti, Elisa Leonardelli, Daniela Trotta, Raffaele Guarasci, Sara Tonelli

In this work, we contribute to this debate by presenting a 3D video game that was used to collect acceptability judgments on Italian sentences.

CoLA

The Geography of Information Diffusion in Online Discourse on Europe and Migration

no code implementations21 Feb 2024 Elisa Leonardelli, Sara Tonelli

Language (English) is pivotal for information to become transnational and reach far.

Putting Context in Context: the Impact of Discussion Structure on Text Classification

1 code implementation5 Feb 2024 Nicolò Penzo, Antonio Longa, Bruno Lepri, Sara Tonelli, Marco Guerini

We also experiment with different amounts of training data and analyse the topology of local discussion networks in a privacy-compliant way.

Stance Detection text-classification +1

Agreeing to Disagree: Annotating Offensive Language Datasets with Annotators' Disagreement

no code implementations28 Sep 2021 Elisa Leonardelli, Stefano Menini, Alessio Palmero Aprosio, Marco Guerini, Sara Tonelli

Since state-of-the-art approaches to offensive language detection rely on supervised learning, it is crucial to quickly adapt them to the continuously evolving scenario of social media.

Monolingual and Cross-Lingual Acceptability Judgments with the Italian CoLA corpus

1 code implementation Findings (EMNLP) 2021 Daniela Trotta, Raffaele Guarasci, Elisa Leonardelli, Sara Tonelli

The development of automated approaches to linguistic acceptability has been greatly fostered by the availability of the English CoLA corpus, which has also been included in the widely used GLUE benchmark.

CoLA domain classification +1

Empowering NGOs in Countering Online Hate Messages

no code implementations6 Jul 2021 Yi-Ling Chung, Serra Sinem Tekiroglu, Sara Tonelli, Marco Guerini

In this paper, we introduce a novel ICT platform that NGO operators can use to monitor and analyze social media data, along with a counter-narrative suggestion tool.

Management

Abuse is Contextual, What about NLP? The Role of Context in Abusive Language Annotation and Detection

1 code implementation27 Mar 2021 Stefano Menini, Alessio Palmero Aprosio, Sara Tonelli

We first re-annotate part of a widely used dataset for abusive language detection in English in two conditions, i. e. with and without context.

Abusive Language General Classification

Creating a Multimodal Dataset of Images and Text to Study Abusive Language

no code implementations5 May 2020 Alessio Palmero Aprosio, Stefano Menini, Sara Tonelli

We find that users judge the same images in different ways, although the presence of a person in the picture increases the probability to get an offensive comment.

Abusive Language

Adding Gesture, Posture and Facial Displays to the PoliModal Corpus of Political Interviews

no code implementations LREC 2020 Daniela Trotta, Alessio Palmero Aprosio, Sara Tonelli, Annibale Elia

This paper introduces a multimodal corpus in the political domain, which on top of transcribed face-to-face interviews presents the annotation of facial displays, hand gestures and body posture.

A 3D Role-Playing Game for Abusive Language Annotation

no code implementations LREC 2020 Federico Bonetti, Sara Tonelli

Gamification has been applied to many linguistic annotation tasks, as an alternative to crowdsourcing platforms to collect annotated data in an inexpensive way.

Abusive Language

A System to Monitor Cyberbullying based on Message Classification and Social Network Analysis

no code implementations WS 2019 Stefano Menini, Giovanni Moretti, Michele Corazza, Elena Cabrio, Sara Tonelli, Serena Villata

Social media platforms like Twitter and Instagram face a surge in cyberbullying phenomena against young users and need to develop scalable computational methods to limit the negative consequences of this kind of abuse.

Abusive Language General Classification

Novel Event Detection and Classification for Historical Texts

no code implementations CL 2019 Rachele Sprugnoli, Sara Tonelli

However, the recognition and elaboration of events is a crucial step when dealing with historical texts Particularly in the current era of massive digitization of historical sources: Research in this domain can lead to the development of methodologies and tools that can assist historians in enhancing their work, while having an impact also on the field of Natural Language Processing.

Classification Event Detection +1

Neural Text Simplification in Low-Resource Conditions Using Weak Supervision

no code implementations WS 2019 Alessio Palmero Aprosio, Sara Tonelli, Marco Turchi, Matteo Negri, Mattia A. Di Gangi

Inspired by the machine translation field, in which synthetic parallel pairs generated from monolingual data yield significant improvements to neural models, in this paper we exploit large amounts of heterogeneous data to automatically select simple sentences, which are then used to create synthetic simplification pairs.

Machine Translation Sentence +3

Creating a WhatsApp Dataset to Study Pre-teen Cyberbullying

no code implementations WS 2018 Rachele Sprugnoli, Stefano Menini, Sara Tonelli, Filippo Oncini, Enrico Piras

Although WhatsApp is used by teenagers as one major channel of cyberbullying, such interactions remain invisible due to the app privacy policies that do not allow ex-post data collection.

MUSST: A Multilingual Syntactic Simplification Tool

no code implementations IJCNLP 2017 Carolina Scarton, Alessio Palmero Aprosio, Sara Tonelli, Tamara Mart{\'\i}n Wanton, Lucia Specia

Our implementation includes a set of general-purpose simplification rules, as well as a sentence selection module (to select sentences to be simplified) and a confidence model (to select only promising simplifications).

Lexical Simplification Sentence +1

Topic-Based Agreement and Disagreement in US Electoral Manifestos

no code implementations EMNLP 2017 Stefano Menini, Federico Nanni, Simone Paolo Ponzetto, Sara Tonelli

We present a topic-based analysis of agreement and disagreement in political manifestos, which relies on a new method for topic detection based on key concept clustering.

Clustering

Building timelines of soccer matches from Twitter

1 code implementation RANLP 2017 Amosse Edouard, Elena Cabrio, Sara Tonelli, Nhan Le-Thanh

This demo paper presents a system that builds a timeline with salient actions of a soccer game, based on the tweets posted by users.

Named Entity Recognition (NER)

You'll Never Tweet Alone: Building Sports Match Timelines from Microblog Posts

no code implementations RANLP 2017 Amosse Edouard, Elena Cabrio, Sara Tonelli, Nhan Le-Thanh

In this paper, we propose an approach to build a timeline with actions in a sports game based on tweets.

Graph-based Event Extraction from Twitter

no code implementations RANLP 2017 Amosse Edouard, Elena Cabrio, Sara Tonelli, Nhan Le-Thanh

Detecting which tweets describe a specific event and clustering them is one of the main challenging tasks related to Social Media currently addressed in the NLP community.

Clustering Event Extraction +1

RAMBLE ON: Tracing Movements of Popular Historical Figures

no code implementations EACL 2017 Stefano Menini, Rachele Sprugnoli, Giovanni Moretti, Enrico Bignotti, Sara Tonelli, Bruno Lepri

We present RAMBLE ON, an application integrating a pipeline for frame-based information extraction and an interface to track and display movement trajectories.

The Content Types Dataset: a New Resource to Explore Semantic and Functional Characteristics of Texts

no code implementations EACL 2017 Rachele Sprugnoli, Tommaso Caselli, Sara Tonelli, Giovanni Moretti

This paper presents a new resource, called Content Types Dataset, to promote the analysis of texts as a composition of units with specific semantic and functional roles.

Classification General Classification +1

Agreement and Disagreement: Comparison of Points of View in the Political Domain

no code implementations COLING 2016 Stefano Menini, Sara Tonelli

The automated comparison of points of view between two politicians is a very challenging task, due not only to the lack of annotated resources, but also to the different dimensions participating to the definition of agreement and disagreement.

Position Sentiment Analysis

CATENA: CAusal and TEmporal relation extraction from NAtural language texts

1 code implementation COLING 2016 Paramita Mirza, Sara Tonelli

The effects of the interaction between the temporal and the causal components, although limited, yield promising results and confirm the tight connection between the temporal and the causal dimension of texts.

General Classification Question Answering +4

On the contribution of word embeddings to temporal relation classification

no code implementations COLING 2016 Paramita Mirza, Sara Tonelli

Temporal relation classification is a challenging task, especially when there are no explicit markers to characterise the relation between temporal entities.

Classification General Classification +5

PreMOn: a Lemon Extension for Exposing Predicate Models as Linked Data

no code implementations LREC 2016 Francesco Corcoglioniti, Marco Rospocher, Alessio Palmero Aprosio, Sara Tonelli

We introduce PreMOn (predicate model for ontologies), a linguistic resource for exposing predicate models (PropBank, NomBank, VerbNet, and FrameNet) and mappings between them (e. g, SemLink) as Linked Open Data.

NLP and Public Engagement: The Case of the Italian School Reform

no code implementations LREC 2016 Tommaso Caselli, Giovanni Moretti, Rachele Sprugnoli, Sara Tonelli, Damien Lanfrey, Donatella Solda Kutzmann

In this paper we present PIERINO (PIattaforma per l{'}Estrazione e il Recupero di INformazione Online), a system that was implemented in collaboration with the Italian Ministry of Education, University and Research to analyse the citizens{'} comments given in {\#}labuonascuola survey.

CROMER: a Tool for Cross-Document Event and Entity Coreference

1 code implementation LREC 2014 Christian Girardi, Manuela Speranza, Rachele Sprugnoli, Sara Tonelli

In this paper we present CROMER (CROss-document Main Events and entities Recognition), a novel tool to manually annotate event and entity coreference across clusters of documents.

Coreference Resolution Retrieval

Improving the Recall of a Discourse Parser by Constraint-based Postprocessing

no code implementations LREC 2012 Sucheta Ghosh, Richard Johansson, Giuseppe Riccardi, Sara Tonelli

We describe two constraint-based methods that can be used to improve the recall of a shallow discourse parser based on conditional random field chunking.

Chunking Semantic Role Labeling

Cannot find the paper you are looking for? You can Submit a new open access paper.