Ara es mostren els items 1-20 de 42

  • A Bootstrapping architecture for time expression recognition in unlabelled corpora via syntactic-semantic patterns 

    Poveda Poveda, Jordi; Surdeanu, Mihai; Turmo Borras, Jorge (2007-06)
    Report de recerca
    Accés obert
    In this paper we describe a semi-supervised approach to the extraction of time expression mentions in large unlabelled corpora based on bootstrapping. Bootstrapping techniques rely on a relatively small amount of initial ...
  • A Constraint-Based Hypergraph Partitioning Approach to Coreference Resolution 

    Sapena Masip, Emilio; Padró, Lluís; Turmo Borras, Jorge (2013-12)
    Article
    Accés obert
    This work is focused on research in machine learning for coreference resolution. Coreference resolution is a natural language processing task that consists of determining the expressions in a discourse that refer to the ...
  • A global relaxation labeling approach to coreference resolution 

    Sapena Masip, Emilio; Padró, Lluís; Turmo Borras, Jorge (2010)
    Text en actes de congrés
    Accés restringit per política de l'editorial
    This paper presents a constraint-based graph partitioning approach to coreference resolution solved by relaxation labeling. The approach combines the strengths of groupwise classifiers and chain formation methods in ...
  • A graph partitioning approach to coreference resolution 

    Sapena Masip, Emilio; Padró, Lluís; Turmo Borras, Jorge (2009-01)
    Report de recerca
    Accés obert
    This report presents a graph partitioning approach given a set of constraints to resolve coreferences. Coreference resolution is the task of determining which referring expressions in a discourse refer to the same entity. ...
  • A graph partitioning approach to entity disambiguation using uncertain information 

    Sapena Masip, Emilio; Padró, Lluís; Turmo Borras, Jorge (Springer, 2008-08-31)
    Text en actes de congrés
    Accés restringit per política de l'editorial
    This paper presents a method for Entity Disambiguation in Information Extraction from different sources in the web. Once entities and relations between them are extracted, it is needed to determine which ones are referring ...
  • A question-driven information system adaptable via information extraction techniques 

    Sapena Masip, Emilio; González Pérez, Manuel; Padró, Lluís; Turmo Borras, Jorge (2008-06)
    Report de recerca
    Accés obert
    This paper presents a system is composed by two main parts: The Information Extraction Process, which crawls the web and extracts all relevant knowledge that is then stored in the database, and the Question Processor which ...
  • Alias assignment in information extraction 

    Sapena Masip, Emilio; Padró, Lluís; Turmo Borras, Jorge (-, 2007-01-31)
    Text en actes de congrés
    Accés restringit per política de l'editorial
    This paper presents a general method for alias assignment task in information extraction. We compared two approaches to face the problem and learn a classifier. The first one quantifies a global similarity between the alias ...
  • An evaluation framework based on gold standard models for definition question answering 

    Kanaan Izquierdo, Samir; Turmo Borras, Jorge (2006-05)
    Report de recerca
    Accés obert
    This paper presents a weak supervised evaluation framework for definition question answering (DefQA) called Solon. It automatically evaluates a set of DefQA systems using existing human definitions as gold standard models. ...
  • Automatically extracting translation links using a wide coverage semantic taxonomy 

    Rigau Claramunt, German; Rodríguez Hontoria, Horacio; Turmo Borras, Jorge (1995-01-01)
    Report de recerca
    Accés obert
    TGE (Tlink Generator Environment) is a system for semi-automatically extracting translation links. The system was developed within the ACQUILEX II project as a tool for supporting the construction of a multi-lingual lexical ...
  • Comparing non-parametric ensemble methods for document clustering 

    González Pellicer, Edgar; Turmo Borras, Jorge (Springer Verlag, 2008)
    Text en actes de congrés
    Accés restringit per política de l'editorial
    The biases of individual algorithms for non-parametric document clustering can lead to non-optimal solutions. Ensemble clustering methods may overcome this limitation, but have not been applied to document collections. ...
  • Coreference resolution survey 

    Sapena Masip, Emilio; Padró, Lluís; Turmo Borras, Jorge (2008-12)
    Report de recerca
    Accés obert
    This survey is an extended summarization of state of the art of coreference resolution. The key concepts related to coreference and anaphora are presented, the most relevant approaches to coreference resolution are discussed, ...
  • Del texto a la información 

    Atserias Batalla, Jordi; Castell Ariño, Núria; Catala Roig, Neus; Rodríguez Hontoria, Horacio; Turmo Borras, Jorge (1998-03)
    Report de recerca
    Accés obert
    In the last years, software applications centered on Natural Language Processing (NLP) have experimented a great significance, especially access to neither unrestricted, nor codified, textual information. In this ...
  • FEMsum at DUC 2006: Semantic-based approach integrated in a Flexible Eclectic Multitask Summarizer Architecture 

    Fuentes Fort, Maria; Rodríguez Hontoria, Horacio; Turmo Borras, Jorge; Ferrés Domènech, Daniel (2006)
    Text en actes de congrés
    Accés obert
    In order to face different requirements at TALP Research Center we have built a highly parameterized environment allowing to instantiate specific summarizers for different summarization tasks in different languages. This ...
  • FEMsum: A flexible eclectic multitask summarizer architecture evaluated in multidocument tasks 

    Fuentes Fort, Maria; Rodríguez Hontoria, Horacio; Turmo Borras, Jorge (2007-01)
    Report de recerca
    Accés obert
    This article describes two types of summarization approaches integrated in a flexible architecture for multitask summarization. The first type is based on the use of lexical features, while the second one is grounded on ...
  • Hacia una clasificación verbal automática para el español: estudio sobre la relevancia de los diferentes tipos y configuraciones de información sintáctico-semántica 

    Gil Vallejo, Lara; Castellón Masalles, Irene; Coll Florit, Marta; Turmo Borras, Jorge (2015-07)
    Article
    Accés obert
    En este trabajo nos centramos en la adquisición de clasificaciones verbales automáticas para el español. Para ello realizamos una serie de experimentos con 20 sentidos verbales del corpus Sensem. Empleamos diferentes tipos ...
  • Inductive logic programming and its application to the temporal expression chunking problem 

    Poveda Poveda, Jordi; Turmo Borras, Jorge (2007-01)
    Report de recerca
    Accés obert
    This document first introduces general notions about ILP (inductive logic programming), including a basic vocabulary of ILP, a typology of ILP systems and a description of the main techniques in ILP. It discusses the ...
  • Introducción a la tarea compartida Tweet-Norm 2013: Normalización léxica de tuits en español 

    Padró, Lluís; Turmo Borras, Jorge; Alegria, Iñaki; Aranberri, Nora; Fresno, Víctor; Samallo, Pablo; San Vicente, Iñaki; Zubiaga, Arkaitz (2013)
    Text en actes de congrés
    Accés obert
    En este artículo se presenta una introducción a la tarea Tweet-Norm 2013 : descripción, corpora, anotación, preproceso, sistemas presentados y resultados obtenidos.
  • Language technologies: question answering in speech transcripts 

    Turmo Borras, Jorge; Surdeanu, Mihai; Galibert, Olivier; Rosset, Sophie (Springer-Verlag, 2009-05-31)
    Capítol de llibre
    Accés restringit per política de l'editorial
    The Question Answering (QA) task consists of providing short, relevant answers to natural language questions. Most QA research has focused on extracting information from text sources, providing a the shortest relevant text ...
  • Non-parametric document clustering by ensemble methods 

    González Pellicer, Edgar; Turmo Borras, Jorge (2008-03)
    Article
    Accés obert
    Los sesgos de los algoritmos individuales para clustering no paramétrico de documentos pueden conducir a soluciones no óptimas. Los métodos de consenso podrían compensar esta limitación, pero no han sido probados sobre ...
  • PHAST: Spoken document retrieval based on sequence alignment 

    Comas Umbert, Pere Ramon; Turmo Borras, Jorge (2008-01)
    Report de recerca
    Accés obert
    This paper presents a new approach to spoken document information retrieval for spontaneous speech corpora. Classical approach to this problem is the use of an automatic speech recognizer (ASR) combined with standard ...