Sara Tonelli

52 papers · 2007–2026 · 9 conferences · across top CS/AI conferences

Achievements

🌈 Renaissance Researcher (6) 🌉 Interdisciplinary Bridge 🐝 Cross-Pollinator (14) 🐣 Hot Topic Early Bird 🧭 Keyword Pioneer 🌍 Conference Polyglot (9) 🏃 Academic Marathon (18) 🗺️ Taxonomy Completionist (60) 🌟 Keyword Trendsetter Combo (6) 🔬 Deep Specialist (15) 🤝 Dynamic Duo (13) 🧬 Topic Evolution 🏆 Keyword Champion (4) ❓ The Questioner (5) 💎 Century Club (51) 🗃️ Keyword Collector (178) 🚀 Conference Pioneer ⚡ Prolific Year (6) 🔥 Unstoppable (17)

Conferences

EMNLP (14) COLING (9) EACL (8) ACL (7) SEMEVAL (5) IJCNLP (3) NAACL (3) AAAI (2) CONLL (1)

Top co-authors

Stefano Menini (13) Alessio Palmero Aprosio (7) Camilla Casula (6) Elisa Leonardelli (6) Marco Guerini (5) Alan Ramponi (5) Paramita Mirza (4) Marco Rovera (4) Bruno Lepri (4) Elena Cabrio (4)

Keywords

text classification (8) offensive language detection (5) hate speech detection (5) information extraction (4) abusive language detection (4) cyberbullying detection (4) large language model (3) multilingual bert (3) synthetic datum (3) frame semantics (3) semantic analysis (3) annotation scheme (3) text mining (2) text simplification (2) social media analysis (2) transfer learning (2) zero-shot learning (2) supervised classification (2) data augmentation (2) multi-task learning (2)

Papers

Don’t Stop the Multi-Party! On Generating Synthetic Written Multi-Party Conversations with Constraints AAAI 2026

Fine-grained Fallacy Detection with Human Label Variation NAACL 2025

Multilingual vs Crosslingual Retrieval of Fact-Checked Claims: A Tale of Two Approaches EMNLP 2025

Multilingual Analysis of Narrative Properties in Conspiracist vs Mainstream Telegram Channels ACL 2025

ModaFact: Multi-paradigm Evaluation for Joint Event Modality and Factuality Detection COLING 2025

ARG2ST at CQs-Gen 2025: Critical Questions Generation through LLMs and Usefulness-based Selection ACL 2025

Job Unfair: An Investigation of Gender and Occupational Bias in Free-Form Text Completions by LLMs EMNLP 2025

TimeFrame: Querying and Visualizing Event Semantic Frames in Time COLING 2024

Don’t Augment, Rewrite? Assessing Abusive Language Detection with Synthetic Data ACL 2024

Delving into Qualitative Implications of Synthetic Data for Hate Speech Detection EMNLP 2024

Do LLMs suffer from Multi-Party Hangover? A Diagnostic Approach to Addressee Recognition and Response Selection in Conversations EMNLP 2024

Putting Context in Context: the Impact of Discussion Structure on Text Classification EACL 2024

A New Annotation Scheme for the Semantics of Taste COLING 2024

BiRDy: Bullying Role Detection in Multi-Party Chats AAAI 2023

Why Don’t You Do It Right? Analysing Annotators’ Disagreement in Subjective Tasks EACL 2023

Generation-Based Data Augmentation for Offensive Language Detection: Is It Worth It? EACL 2023

Scent Mining: Extracting Olfactory Events, Smell Sources and Qualities EACL 2023

Scent and Sensibility: Perception Shifts in the Olfactory Domain EMNLP 2023

Italian Legislative Text Classification for Gazzetta Ufficiale EMNLP 2023

A Multilingual Benchmark to Capture Olfactory Situations over Time ACL 2022

Features or Spurious Artifacts? Data-centric Baselines for Fair and Robust Hate Speech Detection NAACL 2022

Challenges in Designing Games with a Purpose for Abusive Language Annotation EACL 2021

Fine-Grained Fairness Analysis of Abusive Language Detection Systems with CheckList ACL 2021

Agreeing to Disagree: Annotating Offensive Language Datasets with Annotators’ Disagreement EMNLP 2021

Fine-Grained Fairness Analysis of Abusive Language Detection Systems with CheckList IJCNLP 2021

FrameNet-like Annotation of Olfactory Information in Texts EMNLP 2021

Monolingual and Cross-Lingual Acceptability Judgments with the Italian CoLA corpus EMNLP 2021

Hybrid Emoji-Based Masked Language Models for Zero-Shot Abusive Language Detection EMNLP 2020

FBK-DH at SemEval-2020 Task 12: Using Multi-channel BERT for Multilingual Offensive Language Detection SEMEVAL 2020

FBK-DH at SemEval-2020 Task 12: Using Multi-channel BERT for Multilingual Offensive Language Detection COLING 2020

Neural Text Simplification in Low-Resource Conditions Using Weak Supervision NAACL 2019

A System to Monitor Cyberbullying based on Message Classification and Social Network Analysis ACL 2019

Creating a WhatsApp Dataset to Study Pre-teen Cyberbullying EMNLP 2018

RAMBLE ON: Tracing Movements of Popular Historical Figures EACL 2017

MUSST: A Multilingual Syntactic Simplification Tool IJCNLP 2017

Topic-Based Agreement and Disagreement in US Electoral Manifestos EMNLP 2017

The Content Types Dataset: a New Resource to Explore Semantic and Functional Characteristics of Texts EACL 2017

On the contribution of word embeddings to temporal relation classification COLING 2016

CATENA: CAusal and TEmporal relation extraction from NAtural language texts COLING 2016

Agreement and Disagreement: Comparison of Points of View in the Political Domain COLING 2016

Recognizing Biographical Sections in Wikipedia EMNLP 2015

Classifying Temporal Relations with Simple Features EACL 2014

An Analysis of Causality between Events and its Relation to Temporal Information COLING 2014

FBK: Sentiment Analysis in Twitter with Tweetsted SEMEVAL 2013

Outsourcing FrameNet to the Crowd ACL 2013

Hunting for Entailing Pairs in the Penn Discourse Treebank COLING 2012

Shallow Discourse Parsing with Conditional Random Fields IJCNLP 2011

KX: A Flexible System for Keyphrase eXtraction SEMEVAL 2010

VENSES++: Adapting a deep semantic processing system to the identification of null instantiations SEMEVAL 2010

New Features for FrameNet - WordNet Mapping CONLL 2009

Wikipedia as Frame Information Repository EMNLP 2009

IRST-BP: Preposition Disambiguation based on Chain Clarifying Relationships Contexts SEMEVAL 2007