26/06/2014 - Josu Boldoba - Explotación de Wikipedia para el enriquecimiento de un traductor automático

Title Explotación de Wikipedia para el enriquecimiento de un traductor automático
Speaker Josu Boldoba
Room Omega S-208 Campus Nord - UPC
Date Thu Jun 26, 2014
Time 11:00h
Abstract

Presentaré el trabajo desarrollado en el marco de mi proyecto final de carrera. Discutiré el proceso de explotación de Wikipedia para el desarrollo de traductores automáticos entre inglés y castellano. Dicho proceso incluye (1) la generación de corpus comparables de áreas temáticas específicas a partir de artículos de Wikipedia; (2) la extracción de corpus paralelos a nivel de oraciones a partir de corpus comparables y (3) la utilización de dichas oraciones paralelas para enriquecer un traductor automático. Además de los métodos utilizados, discutiré los resultados obtenidos en cada etapa y expondré futuras líneas de investigación.

Bio Josu Boldoba (A Coruña), se estableció en Barcelona para realizar los estudios de Ingeniería en Informática en la FIB en 2006. Entre 2008 y 2011 compaginó sus estudios con actividades laborales en distintas empresas. Cabe destacar su participación en la empresa GTD, entre 2012 y 2014, en la que participó en proyectos del Centre National d'Études Spatiales (CNES, Francia). En 2014 ha trabajado bajo la supervisión de investigadores del Talp Research Center en tareas de procesamiento de lenguaje natural y recuperación de información.

GE awards winners of Flight Quest 2!

GE has revealed the private leaderboard on Flight Quest 2 -- and four outstanding winners! The competition has been running since August as the second part of GE's Industrial Internet Flight Quest with a challenge to develop algorithms that increase flight efficiencies in real time, reducing delays and maximizing a flight's profitability. Using national airspace data provided by FlightStats, the winning algorithms determine the most efficient flight routes, speeds, and altitudes by taking into account variables such as weather, wind, and airspace restraints. The 1st place model by José Fonollosa proved to be up to 12 percent more efficient when compared to data from actual flights.

Read more: GE awards winners of Flight Quest 2!

25/04/1014 - Miguel Ballesteros - Going to the Roots of Dependency Parsing

Title Going to the Roots of Dependency Parsing
Speaker Miguel Ballesteros
Room Omega-S208 Campus Nord - UPC
Date Fri Apr 25, 2014
Time 11:00h
Abstract

In this seminar I will first introduce transition-based dependency parsing and present the conclusions extracted from a journal paper that I have never had the chance to present in public, besides I'm going to sum up my current, past and future research collaboration projects with some new results and developments.

Dependency trees used in syntactic parsing often include a root node representing a dummy word prefixed or suffixed to the sentence, a device that is generally considered a mere technical convenience and is tacitly assumed to have no impact on empirical results. We demonstrate that this assumption is false and that the accuracy of data-driven dependency parsers can in fact be sensitive to the existence and placement of the dummy root node. In particular, we show that a greedy, left-to-right, arc-eager transition-based parser consistently performs worse when the dummy root node is placed at the beginning of the sentence (following the current convention in data-driven dependency parsing) than when it is placed at the end or omitted completely. Control experiments with an arc-standard transition-based parser and an arc-factored graph- based parser reveal no consistent preferences but nevertheless exhibit considerable variation in results depending on root placement. We conclude that the treatment of dummy root nodes in data-driven dependency parsing is an underestimated source of variation in experiments and may also be a parameter worth tuning for some parsers.

Slides  

Subcategories

  • Join us

    Job Offers and Research Positions

  • Awards

    Scientific awards Best: Publications, Thesis, Demos, ...

  • Seminars

    Framework to promote research related with Natural Language Processing or Speech Processing.

  • Thesis

    TALP PhD dissertation

  • Events

    Information about Courses, Conferences, workshops, talks, ...

  • Call For Papers

    Relevant Conference, workshops or special issues call for papers announcement

  • Relevant Publications
  • Members

    Professors, students and colaborators visiting TALP.

    New members incorporation and former members carreer.

  • Projects

    TALP research and innovation projects

  • Press

    Selected articles and reports about the TALP Research Center taken from the international press

  • Formation

Additional information