Rocco Tripodi

Rocco Tripodi
University of Bologna | UNIBO · Department of Modern Languages, Literatures and Cultures LILEC

PhD

About

43
Publications
7,391
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
274
Citations
Citations since 2016
33 Research Items
262 Citations
20162017201820192020202120220102030405060
20162017201820192020202120220102030405060
20162017201820192020202120220102030405060
20162017201820192020202120220102030405060
Additional affiliations
February 2020 - present
Sapienza University of Rome
Position
  • PostDoc Position
Description
  • Sapienza NLP
September 2018 - present
Università Ca' Foscari Venezia
Position
  • Professor (Associate)
Description
  • Digital Text Analysis
June 2017 - January 2020
Università Ca' Foscari Venezia
Position
  • PostDoc Position

Publications

Publications (43)
Preprint
In recent years we have seen the exponential growth of applications, including dialogue systems, that handle sensitive personal information. This has brought to light the extremely important issue regarding personal data protection in virtual environments. Firstly, a performing model should be able to distinguish sentences with sensitive content fr...
Conference Paper
Full-text available
In this paper, we present an evaluation of sentence representation models on the paraphrase detection task. The evaluation is designed to simulate a real-world problem of plagiarism and is based on one of the most important cases of forgery in modern history: the so-called "Protocols of the Elders of Zion". The sentence pairs for the evaluation are...
Article
Full-text available
We explore through the lens of distant reading the evolution of discourse on Jews in France during the XIX century. We analyze a large textual corpus including heterogeneous sources—literary works, periodicals, songs, essays, historical narratives—to trace how Jews are associated to different semantic domains, and how such associations shift over t...
Conference Paper
Full-text available
Multilingual and cross-lingual Semantic Role Labeling (SRL) have recently garnered increasing attention as multilingual text representation techniques have become more effective and widely available. While recent work has attained growing success, results on gold multilingual benchmarks are still not easily comparable across languages, making it di...
Conference Paper
Full-text available
The lexical substitution task aims at generating a list of suitable replacements for a target word in context, ideally keeping the meaning of the modified text unchanged. While its usage has increased in recent years, the paucity of annotated data prevents the finetuning of neural models on the task, hindering the full fruition of recently introduc...
Poster
Full-text available
Despite the recent great success of the sequence-to-sequence paradigm in Natural Language Processing, the majority of current studies in Semantic Role Labeling (SRL) still frame the problem as a sequence labeling task. In this paper we go against the flow and propose GSRL (Generating Senses and RoLes), the first sequence-to-sequence model for end-t...
Conference Paper
Full-text available
Despite the recent great success of the sequence-to-sequence paradigm in Natural Language Processing, the majority of current studies in Semantic Role Labeling (SRL) still frame the problem as a sequence labeling task. In this paper we go against the flow and propose GSRL (Generating Senses and RoLes), the first sequence-to-sequence model for end-t...
Conference Paper
Full-text available
The lexical substitution task aims at finding suitable replacements for words in context. It has proved to be useful in several areas, such as word sense induction and text simplification, as well as in more practical applications such as writing-assistant tools. However, the paucity of annotated data has forced researchers to apply mainly unsuperv...
Conference Paper
In this work we introduce Adversarial Attacks against Abuse (AAA), a new evaluation strategy and associated metric that better captures a model's performance on certain classes of hard-to-classify microposts, and for example penalises systems which are biased on low-level lexical features. It does so by adversarially modifying the model developer's...
Conference Paper
Full-text available
Graph-based semantic parsing aims to represent textual meaning through directed graphs. As one of the most promising general-purpose meaning representations, these structures and their parsing have gained a significant interest momentum during recent years, with several diverse formalisms being proposed. Yet, owing to this very heterogeneity, most...
Conference Paper
Full-text available
Abstract Meaning Representation (AMR) is a popular formalism of natural language that represents the meaning of a sentence as a semantic graph. It is agnostic about how to derive meanings from strings and for this reason it lends itself well to the encoding of semantics across languages. However, cross-lingual AMR parsing is a hard task, because tr...
Conference Paper
Full-text available
Game-theoretic models, thanks to their intrinsic ability to exploit contextual information, have shown to be particularly suited for the Word Sense Disambiguation task. They represent ambiguous words as the players of a non cooperative game and their senses as the strategies that the players can select in order to play the games. The interaction am...
Conference Paper
Full-text available
We investigate some aspects of the history of antisemitism in France, one of the cradles of modern antisemitism, using diachronic word embeddings. We constructed a large corpus of French books and periodicals issues that con- tain a keyword related to Jews and performed a diachronic word embedding over the 1789- 1914 period. We studied the changes...
Poster
1. Introduction A selection of historical textile fragments from the collection of Moisè Michelangelo Guggenheim, ranging from XV to XVIII century, has been investigated by means of non-invasive techniques in order to identify the coloring materials. The selected collection was donated to the Venetian School of Art applied to Industry (currently “M...
Article
A selection of historical textile fragments from the Venetian art dealer Moisè Michelangelo Guggenheim collection, ranging from XV to XVIII century, has been investigated by means of non-invasive techniques in order to reveal the coloring materials. Imagingwas preliminarily used to visually investigate the selected artwork fragments in order to inv...
Article
Full-text available
Motivated by the observation that network-based methods for the automatic prediction of protein functions can greatly benefit from exploiting both the similarity between proteins and the similarity between functional classes (as encoded, e.g., in the Gene Ontology), in this paper we propose a novel approach to the problem, based on the notion of a...
Chapter
Word Sense Disambiguation (WSD) is the task of identifying the intended sense of a word in a computational manner based on the context in which it appears. Understanding the ambiguity of natural languages is considered an AI-hard problem. Computational problems like this are the central objectives of Artificial Intelligence (AI) and Natural Languag...
Poster
Full-text available
Analysis of Italian Word Embeddings
Article
Full-text available
In this work we analyze the performances of two of the most used word embeddings algorithms, skip-gram and continuous bag of words on Italian language. These algorithms have many hyper-parameter that have to be carefully tuned in order to obtain accurate word representation in vectorial space. We provide an accurate analysis and an evaluation, show...
Article
Full-text available
This paper presents a new model for word sense disambiguation formulated in terms of evolutionary game theory, where each word to be disambiguated is represented as a node on a graph whose edges represent word relations and senses are represented as classes. The words simultaneously update their class membership preferences according to the senses...
Conference Paper
In this work we propose a game theoretic model for document clustering. Each document to be clustered is represented as a player and each cluster as a strategy. The players receive a reward interacting with other players that they try to maximize choosing their best strategies. The geometry of the data is modeled with a weighted graph that encodes...
Conference Paper
In this article we propose a method to refine the clustering results obtained with the nonnegative matrix factorization (NMF) technique, imposing consistency constraints on the final labeling of the data. The research community focused its effort on the initialization and on the optimization part of this method, without paying attention to the fina...
Article
Full-text available
In this work we propose a game theoretic model for document clustering. Each document to be clustered is represented as a player and each cluster as a strategy. The players receive a reward interacting with other players that they try to maximize choosing their best strategies. The geometry of the data is modeled with a weighted graph that encodes...
Conference Paper
Full-text available
In this paper we present four experiments on the analysis Italian social media texts using a linguistically-based semantic approach. The experiments are respectively: two on newspaper articles about two political crises, one on a twitter corpus centered on political themes, and one on a case study of strategic plan programs of candidates to the pre...
Article
Full-text available
In this paper we present an unsupervised ap- proach to word sense disambiguation based on evolutionary game theory. In our algorithm each word to be disambiguated is represented as a node on a graph and each sense as a class. The algorithm performs a consistent class as- signment of senses according to the similarity information of each word with t...
Conference Paper
Full-text available
The success of a newspaper article for the public opinion can be measured by the degree in which the journalist is able to report and modify (if needed) attitudes, opinions, feelings and political beliefs. We present a symbolic system for Italian, derived from GETARUNS, which integrates a range of natural language processing tools (also available i...
Conference Paper
Full-text available
As it is known, the success of a newspaper article for the public opinion can be measured by the degree in which the journalist is able to report and modify (if needed) attitudes, opinions, feelings and political beliefs. We present a symbolic system for Italian, derived from GETARUNS, which integrates a range of natural language processing tools w...
Conference Paper
Full-text available
The success of a newspaper article for the public opinion can be measured by the degree in which the journalist is able to report and modify (if needed) attitudes, opinions, feelings and political beliefs. We present a symbolic system for Italian, derived from GETARUNS, which integrates a range of natural language processing tools with the intent t...
Article
Full-text available
We present a system for Question Answering which computes a prospective answer from Logical Forms produced by a full-fledged NLP for text understanding, and then maps the result onto schemata in SPARQL to be used for accessing the Semantic Web. As an intermediate step, and whenever there are complex concepts to be mapped, the system looks for a cor...
Chapter
Full-text available
We present an experiment evaluating the contribution of a system called GReG for reranking the snippets returned by Google’s search engine in the 10 hits presented to the user and captured by the use of Google’s API. The evaluation aims at establishing whether or not the introduction of deep linguistic information may improve the accuracy of Google...
Article
Full-text available
We present a system for Question Answering which computes a prospective answer from Logical Forms produced by a full-fledged NLP for text understanding, and then maps the result onto schemata in SPARQL to be used for accessing the Semantic Web. It is just by the internal structure of the Logical Form that we are able to produce a suitable and meani...
Article
Full-text available
In this paper we present two new mechanisms we created in VENSES, the system for semantic evaluation of the University of Venice. The first mechanism is used to match predicate-argument structures with different governors, a verb and a noun, respectively in the Hypothesis and the Text. It can be defined Augmented Finite State Automata (FSA) which a...

Network

Cited By

Projects

Projects (4)
Project
Abstract Meaning representation for English and cross-lingually as an interlingua.
Project
Analysis of word embeddings for Italian language
Project
The project aims at a better understanding of the mechanisms and dynamics of information circulating in social media and digital news. To achieve this goal it will combine methods from game theory, complex networks, dynamical systems and text analysis. Funded by the European Union’s Horizon 2020 research and innovation programme under grant agreement No 732942. www.odycceus.eu