Donostia, Basque Country (2009)
Eneko Agirre, Donostia Basque Counntry, Bernardo Magnini, German Rigau
This paper presents a first attempt of an application-driven evaluation exercise of WSD. We used a CLIR testbed from the Cross Lingual Evaluation Forum. The expansion, indexing and retrieval...
IRST-BP: Web People Search Using Name Entities (2009)
Octavian Popescu, Bernardo Magnini
In this paper we describe a person clustering system for web pages and report the results we have obtained on the test set of the Semeval 2007 Web Person Search task. Deciding which particular person...
Elena Cabrio, Milen Kouylekov, Bernardo Magnini, Matteo Negri, Laura Hasler, Constantin Orasan, ...
This paper presents the QALL-ME benchmark, a multilingual resource of annotated spoken requests in the tourism domain, freely available for research purposes. The languages currently involved in the...
Answer-Driven Reasoning as a Framework for Intelligent Information Access (2009)
Matteo Negri, Bernardo Magnini, Hristo Tanev
Abstract. This paper presents a general overview of answer-driven reasoning, which may serve as a common framework for a variety of Information Retrieval related activities. The underlying assumption...
Recognising Textual Entailment Challenge (2008)
Roy Bar-haim, Ido Dagan, Bill Dolan, Lisa Ferro, Danilo Giampiccolo, Bernardo Magnini, ...
This paper describes the Second PASCAL
Ontology Population from Textual Mentions: Task Definition and Benchmark (2008)
Bernardo Magnini, Emanuele Pianta, Octavian Popescu, Manuela Speranza
In this paper we propose and investigate Ontology Population from Textual Mentions (OPTM), a sub-task of Ontology Population from text where we assume that mentions for several kinds of entities...
first Recognising Textual Entailment (RTE-1) Challenge benchmark 3. (2008)
Ido Dagan, Oren Glickman, Bernardo Magnini
Abstract. This paper describes the PASCAL Network of Excellence
SemEval-2007 Task 01: Evaluating WSD on Cross-Language Information Retrieval (2008)
Eneko Agirre, Bernardo Magnini, Arantxa Otegi, German Rigau, Piek Vossen
This paper presents a first attempt of an application-driven evaluation exercise of WSD. We used a CLIR testbed from the Cross Lingual Evaluation Forum. The expansion, indexing and retrieval...
Milen Kouylekov, Matteo Negri, Bernardo Magnini
This report presents the outcomes of the activity carried out at FBK-irst for the participation in the CLEF-2007 Main QA track. Both the major improvements over last year’s version of the DIOGENE...
Overview of the CLEF 2006 Multilingual Question Answering Track (2008)
Bernardo Magnini, Danilo Giampiccolo, Pamela Forner, Christelle Ayache, Valentin Jijkoun, Anselmo Peñas, ...
Having being proposed for the fourth time, the QA at CLEF track has confirmed a still raising interest from the research community, recording a constant increase both in the number of participants...
I From Mentions to Ontology: A Pilot Study (2008)
Octavian Popescu, Bernardo Magnini, Emanuele Pianta, Luciano Serafini, Manuela Speranza
Abstract — In this paper we propose a pilot study aimed at an indepth comprehension of the phenomena underlying Ontology Population from text. The study has been carried out on a collection of...
ITC-irst at TREC-2003: the DIOGENE QA system (2008)
Milen Kouylekov, Bernardo Magnini, Matteo Negri, Hristo Tanev
This paper describes a new version of the DIOGENE Question Answering (QA) system developed at ITC-Irst. The recent updates here presented are targeted to the participation to TREC-2003 and meet the...
The Multilingual Question Answering Track at CLEF (2008)
Bernardo Magnini, Danilo Giampiccolo, Lili Aunimo, Christelle Ayache, Petya Osenova, Anselmo Peñas, ...
This paper presents an overview of the Multilingual Question Answering evaluation campaigns which have been organized at CLEF (Cross Language Evaluation Forum) since 2003. Over the years, the...
The Second PASCAL Recognising Textual Entailment Challenge (2008)
Ido Dagan, Bill Dolan, Lisa Ferro, Danilo Giampiccolo, Bernardo Magnini, ...
This paper describes the Second PASCAL Recognising Textual Entailment Challenge (RTE-2).
Making hidden semantics of hierarchical classifications explicit (2007)
Scientifica E Tecnologica, Magnini B, Serafini L, Speranza M, Bernardo Magnini, ...
submittedforted 17881 outside of ITC and will probably be copyrighted if accepted for publication. It has been issued as a Technical Reportfort 17 dissemination of its contents. In view of the...
Scientifica E Tecnologica, Magnini B, Zanobini S, Luciano Serafini, Bernardo Magnini, Stefano Zanobini
This report has been submittedforted 17881 outside of ITC and will probably be copyrighted if accepted for publication. It has been issued as a Technical Reportfort 17 dissemination of its contents....
Large-scale Evaluation of Context Matching (2007)
Scientifica E Tecnologica, Magnini B, Serafini L, Dona A, Gatti L, Girardi C, ...
This report has been submittedforted 17881 outside of ITC and will probably be copyrighted if accepted for publication. It has been issued as a Technical Reportfort 17 dissemination of its contents....
Making Explicit the Hidden Semantics of Hierarchical Classifications (2007)
Scientifica E Tecnologica, Magnini B, Serafini L, Speranza M, Bernardo Magnini, ...
This report has been submittedforted 17881 outside of ITC and will probably be copyrighted if accepted for publication. It has been issued as a Technical Reportfort 17 dissemination of its contents....
Patterns for Word Sense Disambiguation (2007)
Magnus Sahlgren, Ola Knutsson, Octavian Popescu, Bernardo Magnini, Sense Discriminative
The third PASCAL recognizing textual entailment challenge (2007)
Danilo Giampiccolo, Bernardo Magnini, Ido Dagan, Bill Dolan
This paper presents the Third PASCAL Recognising Textual Entailment Challenge (RTE-3), providing an overview of the dataset creating methodology and the submitted systems. In creating this year’s...
What Syntax can Contribute in Entailment Task (2005)
Ido Dagan, Bernardo Magnini, Oren Glickman, Diana Pérez, Enrique Alfonseca, Lucy V, ...
ii
Recognizing Textual Entailment with Tree Edit Distance Algorithms (2005)
Milen Kouylekov, Bernardo Magnini
This paper summarizes ITC-irst participation in the PASCAL challenge on Recognizing Textual Entailment (RTE). Given a pair of texts (the text and the hypothesis), the core of the approach we present...
From Text to Knowledge for the Semantic Web: the ONTOTEXT Project (2005)
Bernardo Magnini, Matteo Negri, Emanuele Pianta, Lorenza Romano, Manuela Speranza, Luciano Serafini, ...
This paper presents the general objectives of the ONTOTEXT project (From Text to Knowledge for the Semantic Web), and the activities carried out during the first year of its development cycle. First,...
Overview of the CLEF 2004 Multilingual Question Answering Track (2005)
Bernardo Magnini, Ro Vallin, Christelle Ayache, Gregor Erbach, Anselmo Peñas, Maarten De Rijke, ...
Abstract. Following the pilot Question Answering Track at CLEF 2003, a new evaluation exercise for multilingual QA systems took place in 2004. This paper reports on the novelties introduced in the...
Overview of the CLEF 2004 Multilingual Question Answering Track (2005)
Bernardo Magnini, Ro Vallin, Christelle Ayache, Gregor Erbach, Anselmo Peñas, Maarten De Rijke, ...
Following the pilot Question Answering Track at CLEF 2003, a new evaluation exercise for multilingual QA systems took place in 2004. This paper reports on the novelties introduced in the new campaign...
Overview of the CLEF 2005 Multilingual Question Answering Track (2005)
Ro Vallin, Bernardo Magnini, Danilo Giampiccolo, Lili Aunimo, Christelle Ayache, Petya Osenova, ...
Abstract. The general aim of the third CLEF Multilingual Question Answering Track was to set up a common and replicable evaluation framework to test both monolingual and cross-language Question...
Overview of the CLEF 2005 Multilingual Question Answering Track (2005)
Ro Vallin, Bernardo Magnini, Danilo Giampiccolo, Lili Aunimo, Christelle Ayache, Petya Osenova, ...
The general aim of the third CLEF Multilingual Question Answering Track was to set up a common and replicable evaluation framework to test both monolingual and cross-language Question Answering (QA)...
Overview of the CLEF 2005 Multilingual Question Answering Track (2005)
Ro Vallin, Bernardo Magnini, Danilo Giampiccolo, Lili Aunimo, Christelle Ayache, Petya Osenova, ...
The general aim of the third CLEF Multilingual Question Answering Track was to set up a common and replicable evaluation framework to test both monolingual and cross-language Question Answering (QA)...
Hristo Tanev, Milen Kouylekov, Bernardo Magnini, Matteo Negri, Kiril Simov
This year we participated at 4 Question Answering tasks at CLEF: the Italian monolingual (I), Italian-English (I/E), Bulgarian monolingual (B), and Bulgarian-English (B/E) bilingual task. While we...
Cross-language acquisition of semantic models for verbal predicates (2004)
Jordi Atserias, Bernardo Magnini, Octavian Popescu, Eneko Agirre, Aitziber Atutxa, German Rigau, ...
This paper presents a semantic-driven methodology for the automatic acquisition of verbal models. Our approach relies strongly on the semantic generalizations allowed by already existing resources...
Unsupervised domain relevance estimation for word sense disambiguation (2004)
Alfio Gliozzo, Bernardo Magnini
This paper presents Domain Relevance Estimation (DRE), a fully unsupervised text categorization technique based on the statistical estimation of the relevance of a text with respect to a certain...
Unsupervised domain relevance estimation for word sense disambiguation (2004)
Alfio Gliozzo, Bernardo Magnini
This paper presents Domain Relevance Estimation (DRE), a fully unsupervised text categorization technique based on the statistical estimation of the relevance of a text with respect to a certain...
Using WordNet Predicates for Multilingual Named Entity Recognition (2004)
Matteo Negri, Bernardo Magnini
WordNet predicates (WN-PREDS) establish relations between words in a certain language and concepts of a language independent ontology. In this paper we show how WN-PREDS can be profitably used in the...
Revising wordnet domains hierarchy: Semantics, coverage, and balancing (2004)
Luisa Bentivogli, Pamela Forner, Bernardo Magnini, Emanuele Pianta
The continuous expansion of the multilingual information society has led in recent years to a pressing demand for multilingual linguistic resources suitable to be used for different applications. In...
Combining Linguistic Processing and Web Mining for Question Answering: ITC-irst at TREC-2004 (2004)
Hristo Tanev, Milen Kouylekov, Bernardo Magnini
This paper describes the work we have been done in the last year on the DIOGENE Question Answering system developed at ITC-Irst. We present two preliminary experiments showing the possibility of...
Bridging Languages for Question Answering: DIOGENE at CLEF 2003 (2004)
Matteo Negri, Hristo Tanev, Bernardo Magnini
This paper presents the extension of the ITC-irst DIOGENE Question Answering system towards multilinguality. DIOGENE relies on a well tested three-components architecture built in the framework of...
Bridging Languages for Question Answering: DIOGENE at CLEF 2003 (2004)
Matteo Negri, Hristo Tanev, Bernardo Magnini
Abstract. This paper presents the extension of the ITC-irst DIOGENE Question Answering system towards multilinguality. DIOGENE relies on a well tested three-components architecture built in the...
The Multiple Language Question Answering Track at (2003)
Bernardo Magnini, Simone Romagnoli, Ro Vallin
This paper reports on the pilot question answering track that was carried out within the CLEF initiative this year. The track was divided into monolingual and bilingual tasks: monolingual systems...
Creating the DISEQuA Corpus: a Test Set for Multilingual Question Answering (2003)
Bernardo Magnini, Simone Romagnoli, Alessandro Vallin, Jesus Herrera, Anselmo Penas, Victor Peinado, ...
This paper describes the procedure adopted by the three co-ordinators of the CLEF 2003 question answering track (ITC-irst, UNED and ILLC) to create the question set for the monolingual tasks. Despite...
The Multiple Language Question Answering Track at CLEF 2003 (2003)
Bernardo Magnini, Simone Romagnoli, Alessandro Vallin, Jesus Herrera, Anselmo Penas, Victor Peinado, ...
This paper reports on the pilot question answering track that was carried out within the CLEF initiative this year. The track was divided into monolingual and bilingual tasks: monolingual systems...
Creating the DISEQuA Corpus: a Test Set for Multilingual Question Answering (2003)
Bernardo Magnini, Simone Romagnoli, Alessandro Vallin, Jesus Herrera, Anselmo Penas, Victor Peinado, ...
This paper describes the procedure adopted by the three coordinators of the CLEF 2003 question answering track (ITC-irst, UNED and ILLC) to create the question set for the monolingual tasks. Despite...
Scientifica Tecnologica Povo, Magnini B, Serafini L, Speranza M, Bernardo Magnini, ...
Most of the data stored in the Semantic Web are organized in schema models, that can be represented as labeled graphs where labels are short natural language expressions. Examples of schema models...
Making Explicit the Hidden Semantics of Hierarchical Classifications (2003)
Bernardo Magnini, Luciano Serafini, Manuela Speranza
Hierarchical classifications are concept hierarchies used to organize large amounts of documents. File systems, products' taxonomies for the marketplace and the directories provided by Web...
An algorithm for matching contextualized schemas via SAT (2003)
Luciano Serafini, Luciano Serafini, Paolo Bouquet, Paolo Bouquet, Bernardo Magnini, Bernardo Magnini, ...
The development of more and more complex distributed applications over large networks of computers has raised the problem of semantic interoperability across autonomous applications. In this paper we...
Creating the DISEQuA corpus: A test set for multilingual question answering (2003)
Bernardo Magnini, Simone Romagnoli, Ro Vallin
Abstract. This paper describes the procedure adopted by the three coordinators of the CLEF 2003 question answering track (ITC-irst, UNED and ILLC) to create the question set for the monolingual...
The Multiple Language Question Answering Track at (2003)
Bernardo Magnini, Simone Romagnoli, Ro Vallin
Abstract. This paper reports on the pilot question answering track that was carried out within the CLEF initiative this year. The track was divided into monolingual and bilingual tasks: monolingual...
Creating the DISEQuA corpus: A test set for multilingual question answering (2003)
Bernardo Magnini, Simone Romagnoli, Ro Vallin
This paper describes the procedure adopted by the three co-ordinators of the CLEF 2003 question answering track (ITC-irst, UNED and ILLC) to create the question set for the monolingual tasks. Despite...
The Multiple Language Question Answering Track at (2003)
Bernardo Magnini, Simone Romagnoli, Ro Vallin
This paper reports on the pilot question answering track that was carried out within the CLEF initiative this year. The track was divided into monolingual and bilingual tasks: monolingual systems...
Merging Global and Specialized Linguistic Ontologies (2002)
Bernardo Magnini, Manuela Speranza
There is an increasing interest in linguistic ontologies (e.g. WordNet) for a variety of content-based tasks, including conceptual indexing, word sense disambiguation and cross-language information...
The role of domain information in word sense disambiguation (2002)
Bernardo Magnini, Giovanni Pezzulo, Alfio Gliozzo
This paper explores the role of domain information in word sense disambiguation. The underlying hypothesis is that domain labels, such as Medicine, Architecture and Sport, provide a useful way to...
H.: Mining Knowledge from repeated Co-occurrences: DIOGENE at TREC-2002 (2002)
Bernardo Magnini, Matteo Negri, Roberto Prevete, Hristo Tanev
This paper presents a new version of the DIOGENE Question Answering (QA) system developed at ITC-Irst. With respect to our first participation to the TREC QA main task (TREC-2001), the system...
Mining the Web to Validate Answers to Natural Language Questions (2002)
Bernardo Magnini, Matteo Negri, Roberto Prevete, Hristo Tanev
questions
Merging Global and Specialized Linguistic Ontologies (2002)
Bernardo Magnini, Manuela Speranza
There is an increasing interest in linguistic ontologies (e.g. WordNet) for a variety of content-based tasks, including conceptual indexing, word sense disambiguation and cross-language information...
Is it the right answer? exploiting web redundancy for answer validation (2002)
Bernardo Magnini, Matteo Negri, Roberto Prevete, Hristo Tanev
Answer Validation is an emerging topic in Question Answering, where open domain systems are often required to rank huge amounts of candidate answers. We present a novel approach to answer validation...
Towards Automatic Evaluation of Question/Answering Systems (2002)
Bernardo Magnini, Matteo Negri, Roberto Prevete, Hristo Tanev
This paper presents an innovative approach to the automatic evaluation of Question Answering systems. The methodology relies on the use of the Web, considered as an “oracle ” containing all the...
H.: Mining Knowledge from repeated Co-occurrences: DIOGENE at TREC-2002 (2002)
Bernardo Magnini, Matteo Negri, Roberto Prevete, Hristo Tanev
This paper presents a new version of the DIOGENE Question Answering (QA) system developed at ITC-Irst. With respect to our first participation to the TREC QA main task (TREC-2001), the system...
H.: Mining Knowledge from repeated Co-occurrences: DIOGENE at TREC-2002 (2002)
Bernardo Magnini, Matteo Negri, Roberto Prevete, Hristo Tanev
{ magnini,negri,prevete,tanev} @ itc.it This paper presents a new version of the DIOGENE Question Answering (QA) system developed at ITCIrst. With respect to our first participation to the TREC QA...
Linguistic based matching of local ontologies (2002)
Bernardo Magnini, Luciano Serafini, Manuela Speranza
This paper describes an automatic algorithm of meaning negotiation that enables semantic interoperability between local overlapping and heterogeneous ontologies. Rather than reconciling differences...
Building thematic lexical resources by term categorization (2002)
Alberto Lavelli, Bernardo Magnini, Fabrizio Sebastiani
We discuss work in progress in the semi-automatic generation of thematic lexicons by means of term categorization, a novel task employing techniques from information retrieval (IR) and machine...
Comparing statistical and content-based techniques for answer validation on the web (2002)
Bernardo Magnini, Matteo Negri, Roberto Prevete, Hristo Tanev
Abstract. Answer Validation is an emerging topic in Question Answering, where open
Is it the right answer? exploiting web redundancy for answer validation (2002)
Bernardo Magnini, Matteo Negri, Roberto Prevete, Hristo Tanev
Answer Validation is an emerging topic in Question Answering, where open domain systems are often required to rank huge amounts of candidate answers. We present a novel approach to answer validation...
Building Thematic Lexical Resources (2002)
Bootstrapping And Machine, Alberto Lavelli, Bernardo Magnini, Fabrizio Sebastiani
We discuss work in progress in the semi-automatic generation of thematic lexicons by means of term categorization, a novel task employing techniques from information retrieval (IR) and machine...
Comparing statistical and content-based techniques for answer validation on the web (2002)
Bernardo Magnini, Matteo Negri, Roberto Prevete, Hristo Tanev
Abstract. Answer Validation is an emerging topic in Question Answering, where open
H.: Multilingual question/answering the DIOGENE system (2001)
Bernardo Magnini, Matteo Negri, Roberto Prevete, Hristo Tanev
This paper presents the DIOGENE question/answering system developed at ITC-Irst. The system is based on a rather standard architecture which includes three components for question processing, search...
Exploiting lexical expansions and boolean compositions for Web querying (2000)
Bernardo Magnini, Roberto Prevete, Via Sommarive
This paper describes an experiment aiming at evaluating the role of NLP based optimizations (i.e. morphological derivation and synonymy expansion) in web search strategies. Keywords and their...
Experiments in Word Domain Disambiguation for Parallel Texts (2000)
This paper describes some preliminary results about Word Domain Disambigua-tion, a variant of Word Sense Disam-bignation where words in a text are tagged with a domain label in place of a sense...
Exploiting lexical expansions and boolean compositions for Web querying (2000)
Bernardo Magnini, Roberto Prevete, Via Sommarive
This paper describes an experiment aiming at evaluating the role of NLP based optimizations (i.e. morphological derivation and synonymy expansion) in web search strategies. Keywords and their...
Experiments in Word Domain Disambiguation for Parallel Texts (2000)
This paper describes some preliminary results about Word Domain Disambiguation, a variant of Word Sense Disambiguation where words in a text are tagged with a domain label in place of a sense label....
Integrating subject field codes into wordnet (2000)
Bernardo Magnini, Gabriela Cavaglià
In this paper, we present a lexical resource where WordNet synsets are annotated with Subject Field Codes. We discuss both the methodological issues we dealt with and the annotation techniques used....
Coping with wordnet sense proliferation (1998)
Ro Artale, Anna Goy, Bernardo Magnini, Emanuele Pianta
WORDNET makes a great number of fine-grained word sense distinctions. However, what could be seen as an advantage has often been considered a problem from a computational point of view. A great...
Lexical Discrimination with the Italian Version of WordNet (1997)
We present a prototype of the Italian version of WORDNET, a general computational lexical re-source. Some relevant extensions are discussed to make it usable for parsing: in particular we add verbal...
Lexical Discrimination with the Italian Version of (1997)
We present a prototype of the Italian version of WordNet, a general computational lexical resource. Some relevant extensions are discussed to make it usable for parsing: in particular we add verbal...
WordNet for Italian and Its Use for Lexical Discrimination (1997)
Alessandro Artale, Ro Artale, Carlo Strapparava, Bernardo Magnini
We present a prototype of the Italian version of WordNet, a general computational lexical resource. Some relevant extensions are discussed to make it usable for parsing: in particular we add verbal...
Lexical Discrimination with the Italian Version of WORDNET (1997)
Alessandro Artale, Ro Artale, Carlo Strapparava, Bernardo Magnini
We present a prototype of the Italian version of WordNet, a general computational lexical resource. Some relevant extensions are discussed to make it usable for parsing: in particular we add verbal...
Clara Bagnasco, Paolo Bresciani, Bernardo Magnini
Abstract. In this paper we present the TAMIC demonstrator, a natural language centered interface designed to improve the way an average citizen can access existing information of the Public...
Bernardo Magnini, Fabio Ciravegna, Emanuele Pianta
This paper describes a project that aims to develop a large-size Lexical Knowledge Base (LKB) for the Italian language. The project began because presently there is no LKB available for Italian, on...
Specification of Upper Model (1994)
ion : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 10 3.1.4 Dimension: Collectivity : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 11 3.1.5 Dimension: Dimensionality : : : : : :...
An Approach to Multilevel Semantics for Applied Systems (1992)
Alberto Lavelli, Bernardo Magnini
Multilevel semantics has been proposed as a powerful architecture for semantic analysis. We propose a methodology that, while maintaining the generality of the multilevel approach, is able to...