Fabio Massimo Zanzotto

Fabio Massimo Zanzotto
University of Rome Tor Vergata | UNIROMA2 · Dipartimento di Ingegneria dell'Impresa

Associate Professor
Coordinator and Principal Investigator of H2020 KATY Project https://katy-project.eu/

About

166
Publications
60,243
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,886
Citations
Additional affiliations
January 2004 - November 2007
Università degli Studi di Milano-Bicocca
Position
  • Researcher

Publications

Publications (166)
Conference Paper
Full-text available
fMRI and ERP/EEG are two different sources for scanning the brain for building mind state decoders. fMRI produces accurate images but it is expensive and cumbersome. ERP/EEG is cheaper and potentially wearable but it gives more coarse-grain data. Recently the metaphor between machines and brains has been introduced in the context of mind state deco...
Article
Full-text available
In this paper, we propose the distributed tree kernels (DTK) as a novel method to reduce time and space complexity of tree kernels. Using a linear complexity algorithm to compute vectors for trees, we embed feature spaces of tree fragments in low-dimensional spaces where the kernel computation is directly done with dot product. We show that DTKs ar...
Article
Finding threads in textual dialogs is emerging as a need to better organize stored knowledge. We capture this need by introducing the novel task of discovering ongoing conversations in scattered dialog blocks. Our aim in this article is twofold. First, we propose a publicly available testbed for the task by solving the insurmountable problem of pri...
Article
Full-text available
Little by little, newspapers are revealing the bright future that Artificial Intelligence (AI) is building. Intelligent machines will help everywhere. However, this bright future may have a possible dark side: a dramatic job market contraction before its unpredictable transformation. Hence, in a near future, large numbers of job seekers may need fi...
Conference Paper
Full-text available
In this paper, we want to further advance the parallelism between models of the brain and computing machines. We want to apply the same idea underlying neuroimaging techniques to electronic computers. Applying this parallelism, we can address these two questions: (1) how far we can go with neuroimaging in understanding human mind? (foundational per...
Conference Paper
Full-text available
Hate speech recognizers may mislabel sentences by not considering the different opinions that society has on selected topics. In this paper, we show how explainable machine learning models based on syntax can help to understand the motivations that induce a sentence to be offensive to a certain demographic group. To explore this hypothesis, we use...
Article
Full-text available
Hate speech recognizers (HSRs) can be the panacea for containing hate in social media or can result in the biggest form of prejudice-based censorship hindering people to express their true selves. In this paper, we hypothesized how massive use of syntax can reduce the prejudice effect in HSRs. To explore this hypothesis, we propose Unintended-bias...
Preprint
Full-text available
A longstanding disconnect between the growing number of MHC Class I immunopeptidomic studies and genomic medicine hinders cancer vaccine design. We develop COD-dipp to genomically map the full spectrum of detected canonical and non canonical (non-exonic) MHC Class I antigens from 26 cancer studies. We demonstrate that patient mutations in regions o...
Preprint
Full-text available
Pre-trained Transformers are challenging human performances in many natural language processing tasks. The gigantic datasets used for pre-training seem to be the key for their success on existing tasks. In this paper, we explore how a range of pre-trained natural language understanding models perform on truly novel and unexplored data, provided by...
Chapter
Full-text available
The study of symbolic syntactic interpretations has been the corner- stone of natural language understanding for many years. Today, modern artificial neural networks are widely searched to assess their syntactic ability, through several probing tasks. In this paper, we propose a neural network system that explicitly includes syntactic interpretatio...
Article
Full-text available
Modern AI technologies make use of statistical learners that lead to self-empiricist logic, which, unlike human minds, use learned non-symbolic representations. Nevertheless, it seems that it is not the right way to progress in AI. The structure of symbols—the operations by which the intellectual solution is realized—and the search for strategic re...
Preprint
Full-text available
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. In this paper, we investigate how the use of explicit domain knowledge of conversational designers affects the performance of neural-based dialogue systems. To support this investigati...
Preprint
Full-text available
Word embeddings are powerful dictionaries, which may easily capture language variations. However, these dictionaries fail to give sense to rare words, which are surprisingly often covered by traditional dictionaries. In this paper, we propose to use definitions retrieved in traditional dictionaries to produce word embeddings for rare words. For thi...
Preprint
Full-text available
Documenting cultural heritage by using artificial intelligence (AI) is crucial for preserving the memory of the past and a key point for future knowledge. However, modern AI technologies make use of statistical learners that lead to self-empiricist logic, which, unlike human minds, use learned non-symbolic representations. Nevertheless, it seems th...
Article
Full-text available
The introduction of sophisticated waste treatment plants is making the process of trash sorting and recycling more and more effective and eco-friendly. Studies on Automated Waste Sorting (AWS) are greatly contributing to making the whole recycling process more efficient. However, a relevant issue, which remains unsolved, is how to deal with the lar...
Article
Full-text available
Artificial Intelligence is providing astonishing results, with medicine being one of its favourite playgrounds. Machine Learning and, in particular, Deep Neural Networks are behind this revolution. Among the most challenging targets of interest in medicine are cancer diagnosis and therapies but, to start this revolution, software tools need to be a...
Article
Radiology reports are of core importance for the communication between the radiologist and clinician. A computer-aided radiology report system can assist radiologists in this task and reduce variation between reports thus facilitating communication with the medical doctor or clinician. Producing a well structured, clear, and clinically well-focused...
Article
Full-text available
The dazzling success of neural networks over natural language processing systems is imposing an urgent need to control their behavior with simpler, more direct declarative rules. In this paper, we propose Pat-in-the-Loop as a model to control a specific class of syntax-oriented neural networks by adding declarative rules. In Pat-in-the-Loop, distri...
Article
Full-text available
People tend to have multiple identities or personalities in their real and on-line lives. In the real life, these identities can be even associated with different names used with parents, groups of friends or in formal contexts. In the on-line side of life, the attitude has exploded: people have the possibility to express different identities with...
Article
Full-text available
Parsing is a key task in computer science, with applications in compilers, natural language processing, syntactic pattern matching, and formal language theory. With the recent development of deep learning techniques, several artificial intelligence applications, especially in natural language processing, have combined traditional parsing methods wi...
Preprint
Full-text available
Artificial Intelligence is providing astonishing results, with medicine being one of its favourite playgrounds. In a few decades, computers may be capable of formulating diagnoses and choosing the correct treatment, while robots may perform surgical operations, and conversational agents could interact with patients as virtual coaches. Machine Learn...
Article
A safe “ageing” of Seveso establishments is a challenge for both operators and regulators. To this scope, Seveso III Directive required to integrate the equipment integrity issue into the safety management system for the major accident prevention; at the same time, the Italian Authority adopted a short-cut method for a quick ageing evaluation, whic...
Article
Full-text available
Machine learning (ML) is largely used to develop automatic predictors in migraine classification but automatic predictors for medication overuse (MO) in migraine are still in their infancy. Thus, to understand the benefits of ML in MO prediction, we explored an automated predictor to estimate MO risk in migraine. To achieve this objective, a study...
Preprint
Full-text available
Creativity is one of the driving forces of human kind as it allows to break current understanding to envision new ideas, which may revolutionize entire fields of knowledge. Scientific research offers a challenging environment where to learn a model for the creative process. In fact, scientific research is a creative act in the formal settings of th...
Article
Full-text available
Natural language is inherently a discrete symbolic representation of human knowledge. Recentadvances in machine learning (ML) and in natural language processing (NLP) seem to contra-dict the above intuition: discrete symbols are fading away, erased by vectors or tensors calleddistributedanddistributional representations. However, there is a strict...
Article
Full-text available
Machine learning (ML) has been recently introduced to develop prognostic classification models that can be used to predict outcomes in individual cancer patients. Here, we report the significance of an ML-based decision support system (DSS), combined with random optimization (RO), to extract prognostic information from routinely collected demograph...
Article
Full-text available
Risk prediction of chemotherapy-associated venous thromboembolism (VTE) is a compelling challenge in contemporary oncology, as VTE may result in treatment delays, impaired quality of life, and increased mortality. Current guidelines do not recommend thromboprophylaxis for primary prevention, but assessment of the patient’s individual risk of VTE pr...
Conference Paper
Full-text available
Sommario Le attrezzature industriali in pressione, destinate al contenimento o alla conversione di sostanze pericolose, e i loro componenti sono soggetti a fenomeni di invecchiamento che, nel corso del tempo, possono influenzare i livelli di sicurezza in quanto aumentano il rischio di perdita di contenimento e riducono la impianto. i manifesta come...
Conference Paper
Full-text available
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 (Barbieri et al., 2018). The model builds on the distributed tree embedder also known as distributed tree kernel (Zanzotto and Dell’Arciprete, 2012). Initial results are extremely enc...
Article
Full-text available
Using kernel machine learning (ML) and random optimization (RO) techniques, we recently developed a set of venous thromboembolism (VTE) risk predictors, which could be useful to devise a web interface for VTE risk stratification in chemotherapy-treated cancer patients. This study was designed to validate a model incorporating the two best predictor...
Data
Finding threads in textual dialogs is emerging as a need to better organize stored knowledge. This need is captured by this novel task of discovering ongoing conversations in scattered dialog blocks. Current services organize dialogs in dialog blocks. These blocks are sequences of turns with a definite set of participants and with a precise tempor...
Article
Full-text available
Syntactic parsing is a key task in natural language processing which has been dominated by symbolic, grammar-based syntactic parsers. Neural networks, with their distributed representations, are challenging these methods. In this paper, we want to show that existing parsing algorithms can cross the border and be defined over distributed representat...
Conference Paper
Evaluating disease progression risk is a key issue in medicine that has been revolutionized by the advent of machine learning approaches and the wide availability of medical data in electronic form. It is time to provide physicians with near-to-the-clinical-practice and effective tools to spread this important technological innovation. In this pape...
Article
Objective: To design a precision medicine approach aimed at exploiting significant patterns in data, in order to produce venous thromboembolism (VTE) risk predictors for cancer outpatients that might be of advantage over the currently recommended model (Khorana score). Design: Multiple kernel learning (MKL) based on support vector machines and r...
Conference Paper
Syntactic parsing is a key component of natural language understanding and, traditionally, has a symbolic output. Recently, a new approach for predicting syntactic structures from sentences has emerged: directly producing small and expressive vectors that embed syntactic structures. In this approach, parsing produces distributed representations. I...
Article
Full-text available
In this paper we explore the possibility to merge the world of Compositional Distributional Semantic Models (CDSM) with Tree Kernels (TK). In particular, we will introduce a specific tree kernel (smoothed tree kernel, or STK) and then show that is possibile to approximate such kernel with the dot product of two vectors obtained compositionally from...
Conference Paper
Encoding structural information in low-dimensional vectors is a recent trend in natural language processing that builds on distributed representations [14]. However, although the success in replacing structural information in final tasks, it is still unclear whether these distributed representations contain enough information on original structures...
Article
Distributional semantics has been extended to phrases and sentences by means of composition operations. We look at how these operations affect similarity measurements, showing that similarity equations of an important class of composition methods can be decomposed into operations performed on the subparts of the input phrases. This establishes a st...
Conference Paper
Full-text available
The field of compositional distributional semantics has proposed very interesting and reliable models for accounting the distributional meaning of simple phrases. These models however tend to disregard the syntactic structures when they are applied to larger sentences. In this paper we propose the chunk-based smoothed tree kernels (CSTKs) as a way...
Conference Paper
Full-text available
In this paper, we describe our submission to the Shared Task #1. We tried to follow the underlying idea of the task, that is, evaluating the gap of full-fledged recognizing textual entailment systems with respect to compositional distributional semantic models (CDSMs) applied to this task. We thus submitted two runs: 1) a system obtained with a mac...
Conference Paper
Full-text available
Online algorithms are an important class of learning machines as they are extremely simple and computationally efficient. Kernel methods versions can handle structured data, such as trees, and achieve state-of-the-art performance. However kernelized versions of Online Learning algorithms slow down when the number of support vectors becomes large. T...
Article
Download Free Sample In the last few years, a number of NLP researchers have developed and participated in the task of Recognizing Textual Entailment (RTE). This task encapsulates Natural Language Understanding capabilities within a very simple interface: recognizing when the meaning of a text snippet is contained in the meaning of a second piece o...
Conference Paper
Full-text available
This paper describes the SemEval-2013 Task 5: “Evaluating Phrasal Semantics”. Its first subtask is about computing the semantic similarity of words and compositional phrases of minimal length. The second one addresses deciding the compositionality of phrases in a given context. The paper discusses the importance and background of these subtasks and...
Conference Paper
In this paper, we present a system for the generation of cultural itineraries that exploits conversational agents to implicitly build formal user profiles. The key idea is that the preferences for user profiling are not obtained in a direct way, but acquired during a natural language conversation of the tourists with the system. When the user profi...
Conference Paper
Full-text available
In this paper, we present a system for the generation of cultural itineraries that exploits conversational agents to implicitly build formal user profiles. The key idea is that the preferences for user profiling are not obtained in a direct way, but acquired during a natural language conversation of the tourists with the system. When the user profi...
Conference Paper
In this paper, we present a system for the generation of cultural itineraries that exploits conversational agents to implicitly build formal user profiles. The key idea is that the preferences for user profiling are not obtained in a direct way, but acquired during a natural language conversation of the tourists with the system. When the user profi...
Conference Paper
In this paper, we present a system for the generation of cultural itineraries that exploits conversational agents to implicitly build formal user profiles. The key idea is that the preferences for user profiling are not obtained in a direct way, but acquired during a natural language conversation of the tourists with the system. When the user profi...
Chapter
Full-text available
Senso Comune is an open knowledge base for the Italian language, available through a Web-based collaborative platform, whose construction is in progress. The resource integrates dictionary data coming from both users and legacy resources with an ontological backbone, which provides foundations for a formal characterization of lexical semantic struc...
Chapter
Recognizing Textual Entailment (RTE) is a complex task, and RTE systems themselves tend to be complex as a result. This chapter gives an overview of different approaches that have been developed so far by the RTE community, and lays out a generic architecture which will help to situate our descriptions and analysis of different aspects of RTE syste...
Chapter
The previous chapters have identified the following key tasks that must be performed by end-toend textual inference systems: Conversion of natural language to a meaning representation. The meaning representation must be defined (i.e., What is the set of predicates? Of functions? Of variables?) and the variability of natural language must be handled...
Chapter
Chapter 2 sketches a framework for building textual entailment recognition systems. This chapter outlines the role Machine Learning can play within this framework, based on approaches described in the research literature to date and, in particular, strives to answer the question: how do we characterize and induce a decision function in an RTE syste...
Chapter
The task of Recognizing Textual Entailment is at the core of one of the most enduring goals of Artificial Intelligence and Natural Language Processing: it requires significant advances in Natural Language Understanding, building on progress in learning and inference. It is also, as shown in Chapter 1, a task that encompasses many other long-standin...
Chapter
As described throughout this book, textual entailment recognition requires background knowledge, which captures inference relations both within the language as well as in the external “real world” discussed in texts. Accordingly, practically all entailment systems employ some form of external knowledge in their architecture. Such knowledge has been...
Conference Paper
We report some existing work, inspired by analogies between human thought and machine computation, showing that the informational state of a digital computer can be decoded in a similar way to brain decoding. We then discuss some proposed work that would leverage this analogy to shed light on the amount of information that may be missed by the tech...
Conference Paper
Modern travelers wish to explore the world at their own pace, following their own expectations and cultural interests. The travel industry should adapt to this new market environment. A large part of cultural travels is based on history and historical events, and books are a near endless repository of such facts. Moreover, novels are a friendlier g...
Article
Full-text available
Senso Comune is an open knowledge base for Italian language, available through a Web-based collaborative plaftorm, whose construction is in progress. The resource integrates dictionary data coming from both users and legacy resources with an ontological backbone, which provides foundations for a formal characterization of lexical semantic structure...
Article
Capturing word meaning is one of the challenges of Natural Language Processing (NLP). Formal models of meaning such as ontologies are knowledge repositories used in a variety of applications. To be effectively used, these ontologies have to be large or, at least, adapted to specific domains. This chapter's main goal is to practically contribute to...