40.2k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- University of TrentoIT265 papers
- European Centre for Theoretical Studies in Nuclear Physics and Related AreasIT190 papers
- Istituto Nazionale di Fisica Nucleare, Trento Institute for Fundamental Physics And ApplicationsIT136 papers
- Centre National de la Recherche ScientifiqueFR99 papers
- Istituto Nazionale di Fisica NucleareIT74 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR61 papers
- Istituto di Fotonica e NanotecnologieIT59 papers
- Istituto Nazionale di Fisica Nucleare, Sezione di GenovaIT52 papers
- University of PisaIT50 papers
- Istituto Nazionale di Fisica Nucleare, Sezione di MilanoIT46 papers
- Istituto Nazionale di Fisica Nucleare, Sezione di Roma IIT46 papers
- Istituto Nazionale di Fisica Nucleare, Laboratori Nazionali di FrascatiIT45 papers
39 papers · 1 filter
The Unheard Alternative: Contrastive Explanations for Speech-to-Text Models
Lina Conti, Dennis Fucci, Marco Gaido +3
Contrastive explanations, which indicate why an AI system produced one output (the target) instead of another (the foil), are widely regarded in explainable AI as more informative…
Don't Stop the Multi-Party! On Generating Synthetic Written Multi-Party Conversations with Constraints
Nicolò Penzo, Marco Guerini, Bruno Lepri +2
Written Multi-Party Conversations (WMPCs) are widely studied across disciplines, with social media as a primary data source due to their accessibility. However, these datasets rais…
Is Safer Better? The Impact of Guardrails on the Argumentative Strength of LLMs in Hate Speech Countering
Helena Bonaldi, Greta Damo, Nicolás Benjamín Ocampo +3
The potential effectiveness of counterspeech as a hate speech mitigation strategy is attracting increasing interest in the NLG research community, particularly towards the task of…
A Survey on Automatic Credibility Assessment Using Textual Credibility Signals in the Era of Large Language Models
Ivan Srba, Olesya Razuvayevskaya, João A. Leite +10
In the age of social media and generative AI, the ability to automatically assess the credibility of online content has become increasingly critical, complementing traditional appr…
Do LLMs suffer from Multi-Party Hangover? A Diagnostic Approach to Addressee Recognition and Response Selection in Conversations
Nicolò Penzo, Maryam Sajedinia, Bruno Lepri +2
Assessing the performance of systems to classify Multi-Party Conversations (MPC) is challenging due to the interconnection between linguistic and structural characteristics of conv…
Medical mT5: An Open-Source Multilingual Text-to-Text LLM for The Medical Domain
Iker García-Ferrero, Rodrigo Agerri, Aitziber Atutxa Salazar +10
Research on language technology for the development of medical applications is currently a hot topic in Natural Language Understanding and Generation. Thus, a number of large langu…
Putting Context in Context: the Impact of Discussion Structure on Text Classification
Nicolò Penzo, Antonio Longa, Bruno Lepri +2
Current text classification approaches usually focus on the content to be classified. Contextual aspects (both linguistic and extra-linguistic) are usually neglected, even in tasks…
Creating a silver standard for patent simplification
Silvia Casola, Alberto Lavelli, Horacio Saggion
Patents are legal documents that aim at protecting inventions on the one hand and at making technical knowledge circulate on the other. Their complex style -- a mix of legal, techn…
Benchmarking the Generation of Fact Checking Explanations
Daniel Russo, Serra Sinem Tekiroglu, Marco Guerini
Fighting misinformation is a challenging, yet crucial, task. Despite the growing number of experts being involved in manual fact-checking, this activity is time-consuming and canno…
PET: An Annotated Dataset for Process Extraction from Natural Language Text
Patrizio Bellan, Han van der Aa, Mauro Dragoni +2
Process extraction from text is an important task of process discovery, for which various approaches have been developed in recent years. However, in contrast to other information…
IndoNLI: A Natural Language Inference Dataset for Indonesian
Rahmad Mahendra, Alham Fikri Aji, Samuel Louvan +2
We present IndoNLI, the first human-elicited NLI dataset for Indonesian. We adapt the data collection protocol for MNLI and collect nearly 18K sentence pairs annotated by crowd wor…
Agreeing to Disagree: Annotating Offensive Language Datasets with Annotators' Disagreement
Elisa Leonardelli, Stefano Menini, Alessio Palmero Aprosio +2
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 m…
Monolingual and Cross-Lingual Acceptability Judgments with the Italian CoLA corpus
Daniela Trotta, Raffaele Guarasci, Elisa Leonardelli +1
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 wi…
Is "moby dick" a Whale or a Bird? Named Entities and Terminology in Speech Translation
Marco Gaido, Susana Rodríguez, Matteo Negri +2
Automatic translation systems are known to struggle with rare words. Among these, named entities (NEs) and domain-specific terms are crucial, since errors in their translation can…
Human-in-the-Loop for Data Collection: a Multi-Target Counter Narrative Dataset to Fight Online Hate Speech
Margherita Fanton, Helena Bonaldi, Serra Sinem Tekiroglu +1
Undermining the impact of hateful content with informed and non-aggressive responses, called counter narratives, has emerged as a possible solution for having healthier online comm…
Empowering NGOs in Countering Online Hate Messages
Yi-Ling Chung, Serra Sinem Tekiroglu, Sara Tonelli +1
Studies on online hate speech have mostly focused on the automated detection of harmful messages. Little attention has been devoted so far to the development of effective strategie…
Dealing with training and test segmentation mismatch: FBK@IWSLT2021
Sara Papi, Marco Gaido, Matteo Negri +1
This paper describes FBK's system submission to the IWSLT 2021 Offline Speech Translation task. We participated with a direct model, which is a Transformer-based architecture train…
Mixtures of Deep Neural Experts for Automated Speech Scoring
Sara Papi, Edmondo Trentin, Roberto Gretter +2
The paper copes with the task of automatic assessment of second language proficiency from the language learners' spoken responses to test prompts. The task has significant relevanc…
Summarization, Simplification, and Generation: The Case of Patents
Silvia Casola, Alberto Lavelli
We survey Natural Language Processing (NLP) approaches to summarizing, simplifying, and generating patents' text. While solving these tasks has important practical applications - g…
On Target Segmentation for Direct Speech Translation
Mattia Antonino Di Gangi, Marco Gaido, Matteo Negri +1
Recent studies on direct speech translation show continuous improvements by means of data augmentation techniques and bigger deep learning models. While these methods are helping t…
Gender in Danger? Evaluating Speech Translation Technology on the MuST-SHE Corpus
Luisa Bentivogli, Beatrice Savoldi, Matteo Negri +3
Translating from languages without productive grammatical gender like English into gender-marked languages is a well-known difficulty for machines. This difficulty is also due to t…
MuST-Cinema: a Speech-to-Subtitles corpus
Alina Karakanta, Matteo Negri, Marco Turchi
Growing needs in localising audiovisual content in multiple languages through subtitles call for the development of automatic solutions for human subtitling. Neural Machine Transla…
SemEval-2010 Task 8: Multi-Way Classification of Semantic Relations Between Pairs of Nominals
Iris Hendrickx, Su Nam Kim, Zornitsa Kozareva +6
In response to the continuing research interest in computational semantic analysis, we have proposed a new task for SemEval-2010: multi-way classification of mutually exclusive sem…
Generating Challenge Datasets for Task-Oriented Conversational Agents through Self-Play
Sourabh Majumdar, Serra Sinem Tekiroglu, Marco Guerini
End-to-end neural approaches are becoming increasingly common in conversational scenarios due to their promising performances when provided with sufficient amount of data. In this…