no code implementations • LREC 2022 • Giancarlo Xompero, Michele Mastromattei, Samir Salman, Cristina Giannone, Andrea Favalli, Raniero Romagnoli, Fabio Massimo Zanzotto
In fact, rules from conversational designers used in CLINN significantly outperform a state-of-the-art neural-based dialogue system when trained with smaller sets of annotated dialogues.
1 code implementation • EMNLP 2020 • Fabio Massimo Zanzotto, Andrea Santilli, Leonardo Ranaldi, Dario Onorati, Pierfrancesco Tommasino, Francesca Fallucchi
Syntactic parsers have dominated natural language understanding for decades.
no code implementations • NLPerspectives (LREC) 2022 • Michele Mastromattei, Valerio Basile, Fabio Massimo Zanzotto
Hate speech recognizers may mislabel sentences by not considering the different opinions that society has on selected topics.
no code implementations • 12 Feb 2024 • Federico Ranaldi, Elena Sofia Ruzzetti, Dario Onorati, Leonardo Ranaldi, Cristina Giannone, Andrea Favalli, Raniero Romagnoli, Fabio Massimo Zanzotto
Our results indicate a significant performance drop in GPT-3. 5 on the unfamiliar Termite dataset, even with ATD modifications, highlighting the effect of Data Contamination on LLMs in Text-to-SQL translation tasks.
1 code implementation • 5 Feb 2024 • Michele Mastromattei, Fabio Massimo Zanzotto
This approach maintains model performance while allowing storage of only the optimized subnetwork, leading to significant memory savings.
no code implementations • 14 Nov 2023 • Leonardo Ranaldi, Giulia Pucci, Federico Ranaldi, Elena Sofia Ruzzetti, Fabio Massimo Zanzotto
Reasoning methods, best exemplified by the well-known Chain-of-Thought (CoT), empower the reasoning abilities of Large Language Models (LLMs) by eliciting them to solve complex tasks in a step-by-step manner.
no code implementations • 21 Sep 2023 • Leonardo Ranaldi, Fabio Massimo Zanzotto
Following a correlation between first positions and model choices due to positional bias, we hypothesized the presence of structural heuristics in the decision-making process of the It-LLMs, strengthened by including significant examples in few-shot scenarios.
no code implementations • 23 May 2023 • Leonardo Ranaldi, Elena Sofia Ruzzetti, Davide Venditti, Dario Onorati, Fabio Massimo Zanzotto
In this paper, we performed a large investigation of the bias of three families of CtB-LLMs, and we showed that debiasing techniques are effective and usable.
no code implementations • 8 May 2023 • Leonardo Ranaldi, Elena Sofia Ruzzetti, Fabio Massimo Zanzotto
Pre-trained Language Models such as BERT are impressive machines with the ability to memorize, possibly generalized learning examples.
no code implementations • 3 May 2023 • Elena Sofia Ruzzetti, Federico Ranaldi, Felicia Logozzo, Michele Mastromattei, Leonardo Ranaldi, Fabio Massimo Zanzotto
The impressive achievements of transformers force NLP researchers to delve into how these models represent the underlying structure of natural language.
no code implementations • 27 Sep 2022 • Marco Gerardi, Katarzyna Barud, Marie-Catherine Wagner, Nikolaus Forgo, Francesca Fallucchi, Noemi Scarpato, Fiorella Guadagni, Fabio Massimo Zanzotto
In this paper, we present Active Informed Consent (AIC) as a novel hybrid legal-technological tool to foster the gathering of a large amount of data for machine learning.
no code implementations • 14 Jan 2022 • Leonardo Ranaldi, Aria Nourbakhsh, Arianna Patrizi, Elena Sofia Ruzzetti, Dario Onorati, Francesca Fallucchi, Fabio Massimo Zanzotto
Pre-trained Transformers are challenging human performances in many NLP tasks.
no code implementations • 27 Sep 2021 • Giancarlo A. Xompero, Michele Mastromattei, Samir Salman, Cristina Giannone, Andrea Favalli, Raniero Romagnoli, Fabio Massimo Zanzotto
Incorporating explicit domain knowledge into neural-based task-oriented dialogue systems is an effective way to reduce the need of large sets of annotated dialogues.
no code implementations • Findings (ACL) 2022 • Elena Sofia Ruzzetti, Leonardo Ranaldi, Michele Mastromattei, Francesca Fallucchi, Fabio Massimo Zanzotto
In this paper, we propose to use definitions retrieved in traditional dictionaries to produce word embeddings for rare words.
no code implementations • 1 Oct 2020 • Antonio-Jesús Banegas-Luna, Jorge Peña-García, Adrian Iftene, Fiorella Guadagni, Patrizia Ferroni, Noemi Scarpato, Fabio Massimo Zanzotto, Andrés Bueno-Crespo, Horacio Pérez-Sánchez
Among the most challenging targets of interest in medicine are cancer diagnosis and therapies but, to start this revolution, software tools need to be adapted to cover the new requirements.
1 code implementation • 28 Feb 2020 • Fabio Massimo Zanzotto, Viviana Bono, Paola Vocca, Andrea Santilli, Danilo Croce, Giorgio Gambosi, Roberto Basili
In this paper, we dare to introduce the novel, scientifically and philosophically challenging task of Generating Abstracts of Scientific Papers from abstracts of cited papers (GASP) as a text-to-text task to investigate scientific creativity, To foster research in this novel, challenging task, we prepared a dataset by using services where that solve the problem of copyright and, hence, the dataset is public available with its standard split.
no code implementations • SEMEVAL 2018 • Fabio Massimo Zanzotto, Andrea Santilli
In this paper, we present SyntNN as a way to include traditional syntactic models in multilayer neural networks used in the task of Semeval Task 2 of emoji prediction.
no code implementations • 23 Oct 2017 • Fabio Massimo Zanzotto
Little by little, newspapers are revealing the bright future that Artificial Intelligence (AI) is building.
no code implementations • 24 May 2017 • Fabio Massimo Zanzotto, Giordano Cristini, Giorgio Satta
By showing that CYK can be entirely performed on distributed representations, we open the way to the definition of recurrent layers of CYK-informed neural networks.
no code implementations • 2 Feb 2017 • Lorenzo Ferrone, Fabio Massimo Zanzotto
Natural language is inherently a discrete symbolic representation of human knowledge.