You are here

Manuela Speranza

  • Phone: +39 0461 314521
  • FBK Povo
Short bio

I have been working at ITC-irst, now FBK, since 2000. First, I worked on the SI-TAL (Integrated System for the Automatic Treatment of Language) and on the Edamok projects. From 2004 2006 I worked on the Ontotext project. From 2007 to 2012 I worked on the projects Qall-me, LiveMemories and Meta-Net. More recently, I have worked on the European projects MateCat and NewsReader.

My main interests include evaluation methodologies (see NER 2007, Entity Recognition 2009, NER 2011, EVENTI 2014 and FactA 2016 at EVALITA and TimeLine: Cross-Document Event Ordering at SemEval-2015), entity annotation (see I-CAB), event, temporal information, and co-reference annotation (see the NewsReader MEANTIME corpus), event factuality and negation annotation (see Fact-Ita Bank), and computational lexicography (see MultiWordNet and WordNet Domains).
I was also involved in the overall organization of EVALITA 2007, EVALITA 2009 and EVALITA 2011.

Research interests
corpus annotation evaluation methodologies computational lexicography
Publications
  1. Bernardo Magnini; Luciano Serafini; Manuela Speranza,
    Making Explicit the Hidden Semantics of Hierarchical Classifications,
    AI*IA 2003: Advances in Artificial Intelligence, 8th Congress of the Italian Association for Artificial Intelligence,
    Springer,
    vol.2829,
    2003
    , pp. 436-
    448
    , (AI*IA 2003: Advances in Artificial Intelligence, 8th Congress of the Italian Association for Artificial Intelligence,
    Pisa, Italy,
    2003)
  2. Bernardo Magnini; Luciano Serafini; A. Donà; Laura Gatti; Christian Girardi; Manuela Speranza,
    Large-scale Evaluation of Context Matching,
    Context matching algorithms automatically discover semantic relations between two autonomously developed conceptual representations of two overlapping domains. Although significant work has been carried on the theoretical ground, the empirical evaluation of matching algoritms is still an open are for research. In this paper we introduce CtxMatch, a matching algorithm which applies to symbolic based conceptual representations organized as a hierarchy of concepts. Typical examples of such conceptualizations are electronic market catalogs (e.g., UNSPSC and eCl@ss) and web directories (e.g., Google and Yahoo!). Then, we report on different evaluation experiments, that have been carried out with two main purposes: we wanted to evaluate the \ctxmatch\ algorithm in real, large scale scenarios and to test different evaluation methodologies. Results are to be considered as a first contribution toward shared evaluation practices and resources for context matching algorithms,
    2003
  3. Bernardo Magnini; Luciano Serafini; Manuela Speranza,
    Making explicit the hidden semantics of hierarchical classifications,
    Hierarchical classifications are concept hierarchies used to organize large amounts of documents. File systems, products' taxonomies for the market place and the directories provided by Web portals are common examples of hierarchical classifications. As semi-structured knowledge sources, hierarchical classifications have peculiar features: they differ both from plain texts since they are based on a taxonomy of concepts, and from structured data sources (such as databases and formal ontologies), because many semantic relations are implicit. We propose a methodology for building a semantic interpretation of hierarchical classifications on the basis of the analysis of the taxonomic relations and the linguistic material they contain. We provide a formal semantics for hierarchical classifications and then we use that formal framework to interpret the implicit knowledge represented, by exploring a number of crucial linguistic issues. Relevant phenomena addressed include the disambiguation of polysemous words, the semantics of multiwords, and the interpretation of coordinations. The Web Directories of Google and Yahoo! have been chosen as an evaluation set. We show that there is a considerable amount of information to be made explicit and discuss the performance of an implementation of our analysis,
    2003
  4. Bernardo Magnini; Luciano Serafini; Manuela Speranza,
    Making Explicit the Semantics Hidden in Schema Models,
    2003
  5. Bernardo Magnini; Manuela Speranza,
    Merging Global and Specialized Linguistic Ontologies,
    LREC 2002 Ontolex Workshop,
    2002
    , pp. 43-
    48
    , (LREC 2002 Ontolex Workshop,
    Las Palmas, Canary Islands, Spain,
    27/05/2002 - 31/05/2002)
  6. Bernardo Magnini; Luciano Serafini; Manuela Speranza,
    Linguistic Based Matching of Local Ontologies,
    Workshop on Meaning Negotiation 2002,
    2002
    , pp. 42-
    50
    , (Workshop on Meaning Negotiation 2002,
    held in conjunction with AAAI-2002, Edmonton, Canada,
    2002)
  7. A. Roventini; A. Alonge; F. Bertagna; N. Calzolari; R. Marinelli; Bernardo Magnini; Manuela Speranza; A. Zampolli,
    ItalWordnet: a Large Semantic Database for the Automatic Treatment of the Italian Language,
    First International Conference on Global WordNet,
    2002
    , (First International Conference on Global WordNet,
    Mysore, India,
    21/01/2002 - 25/01/2002)
  8. Bernardo Magnini; Luciano Serafini; Manuela Speranza,
    Using NLP Techniques for Meaning Negotiation,
    VIII Convegno AI*IA,
    2002
    , (VIII Convegno AI*IA,
    Siena, Italy,
    2002)
  9. Bernardo Magnini; Luciano Serafini; Manuela Speranza; S. Zanobini,
    CTXMATCH - A reference schema for Context Matching (V. 1.0),
    We introduce an application combining CBR and collaborative filtering techniques in the music domain. We describe a scenario in which a new kind of recommendation is required suitable to summarize in one suggestion many recommendations. Our claim is that to recommend a set of goods is different from recommending many times a single good. The paper illustrates how a case-based reasoning approach can provide an effective solution to this problem reducing the drawbacks related to the user profiles. CoCoA, a compilation compiler advisor, will be described as a running example of a collaborative case-based recommendation system,
    2002
  10. Bernardo Magnini; Luciano Serafini; Manuela Speranza,
    Making Hidden Semantics of Hierarchical Classifications Explicit,
    Concept hierarchies are semi-structured knowledge repositories used for organizing large amounts of documents. File systems, products taxonomies for the market place and the directories provided by Web portals are common examples of concept hierarchies. We take the perspective in which such knowledge sources are inherently distributed and we address the problem of allowing their interoperability. In this paper first we provide a formal semantics for concept hierarchies and then we use that formal framework to explore a number of linguistic issues crucial for interpreting the implicit knowledge represented there. Relevant phenomena addressed include word sense disambiguation WORDNET(r) has been used as sense repository), the explicitation of multiwords' semantics and the interpretation of coordinations. The Web directories of Google and Yahoo has been considered for a number of case studies,
    2002

Pages