Alessandro Tommasi - Academia.edu (original) (raw)
Uploads
Papers by Alessandro Tommasi
Online Social Networks and Media, Jun 1, 2018
This paper considers online news censorship and it concentrates on censorship of identities. Obfu... more This paper considers online news censorship and it concentrates on censorship of identities. Obfuscating identities may occur for disparate reasons, from military to judiciary ones. In the majority of cases, this happens to protect individuals from being identified and persecuted by hostile people. However, being the collaborative web characterised by a redundancy of information, it is not unusual that the same fact is reported by multiple sources, which may not apply the same restriction policies in terms of censorship. Also, the proven aptitude of social network users to disclose personal information leads to the phenomenon that comments to news can reveal the data withheld in the news itself. This gives us a mean to figure out who the subject of the censored news is. We propose an adaptation of a text analysis approach to unveil censored identities. The approach is tested on a synthesised scenario, which however resembles a real use case. Leveraging a text analysis based on a context classifier trained over snippets from posts and comments of Facebook pages, we achieve promising results. Despite the quite constrained settings in which we operate-such as considering only snippets of very short length-our system successfully detects the censored name, choosing among 10 different candidate names, in more than 50% of the investigated cases. This outperforms the results of two reference baselines. The findings reported in this paper, other than being supported by a thorough experimental methodology and interesting on their own, also pave the way for further investigation on the insidious issues of censorship on the web.
In this work we propose a model to learn conceptual descriptions of categories fromprecategorized... more In this work we propose a model to learn conceptual descriptions of categories fromprecategorized texts. The model is general and parametric, and it captures most of thestatistical approaches to classication as well as allowing the denition of more symboliclearning schemes. The algorithm scheme has been instantiated into three dierent algorithms,which have been implemented and tested on a collection of documents
PiQASso is a Question Answering system based on a combination of modern IR techniques and a serie... more PiQASso is a Question Answering system based on a combination of modern IR techniques and a series of semantic filters for selecting paragraphs containing a justifiable answer. Semantic filtering is based on several NLP tools, including a dependency-based parser, a POS tagger, a NE tagger and a lexical database. Semantic analysis of questions is performed in order to extract keywords used in retrieval queries and to detect the expected answer type. Semantic analysis of retrieved paragraphs includes checking the presence of entities of the expected answer type and extracting logical relations between words. A paragraph is considered to justify an answer if similar relations are present in the question. When no answer passes the filters, the process is repeated applying further levels of query expansions in order to increase recall. We discuss results and limitations of the current implementation.
In Proc. The Semantic …
In this paper, we will introduce BRITE, an Integrated Project sponsored by the European Union sta... more In this paper, we will introduce BRITE, an Integrated Project sponsored by the European Union starting in 2006. The aim of BRITE is to exploit Semantic Web technologies in order to enable interoperation in a transnational scenario, namely processes between institutions ...
The paper describes Redada, a fully-implemented ontology-based relation extraction system that in... more The paper describes Redada, a fully-implemented ontology-based relation extraction system that integrates classical NLP techniques with expert knowledge expressed by ontologies. Experimenting with the system for the task of supporting law enforcement and intelligence activties against money laundering and corruption, exploring information out of Italian newspapers to help in the identification of networks of activity, both legal and illegal, we evaluate the proposed system against a standard baseline approach, and we present our first results.
2010 Second International Conference on Information, Process, and Knowledge Management, 2010
With this paper we describe an ontology-driven system that performs relation extraction over text... more With this paper we describe an ontology-driven system that performs relation extraction over textual data. The system exploits expert knowledge of the domain, including lexical resources, in the form of an ontology to drive the extraction of patterns using manually annotated texts. Such patterns are then applied in order to identify candidates for relation extraction. Paired with basic, reliable named-entitylevel text annotation, this results in the discovery of relations among entities in Italian newspaper articles. In the paper, we describe the system and measure its performance.
Online Social Networks and Media, Jun 1, 2018
This paper considers online news censorship and it concentrates on censorship of identities. Obfu... more This paper considers online news censorship and it concentrates on censorship of identities. Obfuscating identities may occur for disparate reasons, from military to judiciary ones. In the majority of cases, this happens to protect individuals from being identified and persecuted by hostile people. However, being the collaborative web characterised by a redundancy of information, it is not unusual that the same fact is reported by multiple sources, which may not apply the same restriction policies in terms of censorship. Also, the proven aptitude of social network users to disclose personal information leads to the phenomenon that comments to news can reveal the data withheld in the news itself. This gives us a mean to figure out who the subject of the censored news is. We propose an adaptation of a text analysis approach to unveil censored identities. The approach is tested on a synthesised scenario, which however resembles a real use case. Leveraging a text analysis based on a context classifier trained over snippets from posts and comments of Facebook pages, we achieve promising results. Despite the quite constrained settings in which we operate-such as considering only snippets of very short length-our system successfully detects the censored name, choosing among 10 different candidate names, in more than 50% of the investigated cases. This outperforms the results of two reference baselines. The findings reported in this paper, other than being supported by a thorough experimental methodology and interesting on their own, also pave the way for further investigation on the insidious issues of censorship on the web.
In this work we propose a model to learn conceptual descriptions of categories fromprecategorized... more In this work we propose a model to learn conceptual descriptions of categories fromprecategorized texts. The model is general and parametric, and it captures most of thestatistical approaches to classication as well as allowing the denition of more symboliclearning schemes. The algorithm scheme has been instantiated into three dierent algorithms,which have been implemented and tested on a collection of documents
PiQASso is a Question Answering system based on a combination of modern IR techniques and a serie... more PiQASso is a Question Answering system based on a combination of modern IR techniques and a series of semantic filters for selecting paragraphs containing a justifiable answer. Semantic filtering is based on several NLP tools, including a dependency-based parser, a POS tagger, a NE tagger and a lexical database. Semantic analysis of questions is performed in order to extract keywords used in retrieval queries and to detect the expected answer type. Semantic analysis of retrieved paragraphs includes checking the presence of entities of the expected answer type and extracting logical relations between words. A paragraph is considered to justify an answer if similar relations are present in the question. When no answer passes the filters, the process is repeated applying further levels of query expansions in order to increase recall. We discuss results and limitations of the current implementation.
In Proc. The Semantic …
In this paper, we will introduce BRITE, an Integrated Project sponsored by the European Union sta... more In this paper, we will introduce BRITE, an Integrated Project sponsored by the European Union starting in 2006. The aim of BRITE is to exploit Semantic Web technologies in order to enable interoperation in a transnational scenario, namely processes between institutions ...
The paper describes Redada, a fully-implemented ontology-based relation extraction system that in... more The paper describes Redada, a fully-implemented ontology-based relation extraction system that integrates classical NLP techniques with expert knowledge expressed by ontologies. Experimenting with the system for the task of supporting law enforcement and intelligence activties against money laundering and corruption, exploring information out of Italian newspapers to help in the identification of networks of activity, both legal and illegal, we evaluate the proposed system against a standard baseline approach, and we present our first results.
2010 Second International Conference on Information, Process, and Knowledge Management, 2010
With this paper we describe an ontology-driven system that performs relation extraction over text... more With this paper we describe an ontology-driven system that performs relation extraction over textual data. The system exploits expert knowledge of the domain, including lexical resources, in the form of an ontology to drive the extraction of patterns using manually annotated texts. Such patterns are then applied in order to identify candidates for relation extraction. Paired with basic, reliable named-entitylevel text annotation, this results in the discovery of relations among entities in Italian newspaper articles. In the paper, we describe the system and measure its performance.