Recent Submissions

  • IQMT: A framework for automatic machine translation evaluation based on human likeness: Technical manual 2.0l 

    Giménez Linares, Jesús Ángel (2007-06)
    External research report
    Open Access
    This report presents a description and tutorial on the IQMT Framework for Machine Translation Evaluation based on `Human Likeness'. IQMT intends to offer a common workbench on which MT evaluation metrics can be robustly ...
  • Leveraging online user feedback to improve statistical machine translation 

    Formiga, Lluís; Barrón-Cedeño, Alberto; Marquez, Lluis; Henriquez, Carlos A; Mariño Acebal, José Bernardo (2015-09-01)
    Article
    Open Access
    In this article we present a three-step methodology for dynamically improving a statistical machine translation (SMT) system by incorporating human feedback in the form of free edits on the system translations. We target ...
  • Inductive logic programming and its application to the temporal expression chunking problem 

    Poveda Poveda, Jordi; Turmo Borras, Jorge (2007-01)
    External research report
    Open Access
    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 ...
  • SVMs for the temporal expression chunking problem 

    Poveda Poveda, Jordi; Surdeanu, Mihai (2006-11)
    External research report
    Open Access
    This technical report provides a description of the Temporal Expression Chunking problem, which consists in finding the mentions of temporal expressions in free text documents, and reports on the results obtained using SVM ...
  • An evaluation framework based on gold standard models for definition question answering 

    Kanaan Izquierdo, Samir; Turmo Borras, Jorge (2006-05)
    External research report
    Open Access
    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. ...
  • Unsupervised document clustering by weighted combination 

    González Pellicer, Edgar; Turmo Borras, Jorge (2006-05)
    External research report
    Open Access
    This report proposes a novel unsupervised document clustering approach based on weighted combination of individual clusterings. Two non-weighted combination methods are adapted to work in a weighted fashion: a graph based ...
  • Current/historical: An efficient bitemporal storage structure for data warehousing 

    Martín Escofet, Carme; Montero, O; Surroca, C (2005-11)
    External research report
    Open Access
    A Data Warehouse is defined as a time variant set of non-volatile data. This can be easily related to temporal database concepts (i.e. a database supporting Valid Time and Transaction Time is known as a bitemporal database). ...
  • Adaptive generation of multilingual questions and answers from web content 

    Gatius Vila, Marta (Institute of Electrical and Electronics Engineers (IEEE), 2015)
    Conference report
    Open Access
    This article describes the adaptive generation of questions and answers from web content to assist the user when searching for information. The approach proposed integrates user models, domain-restricted knowledge ...
  • On the process of building a process systems engineering ontology using a semi-automatic construction approach 

    Dombayci, Canan; Farreres de la Morena, Xavier; Rodríguez Hontoria, Horacio; Muñoz Mata, Edrisi; Capon Garcia, Elisabeth; Espuña Camarasa, Antonio; Graells Sobré, Moisès (2015-06)
    Article
    Open Access
    This work presents a novel systematic approach for the construction of domain ontologies. The suggested approach uses a semi-automatic construction methodology. For this study, parent-child concept pairs are taken from a ...
  • ESSENCE: a portable methodology for building information extraction systems 

    Catala Roig, Neus (1998-10)
    External research report
    Open Access
    One of the most important issues when constructing an Information Extraction System is how to obtain the knowledge needed for identifying relevant information in a document. A manual approach not only is an expensive ...

View more