1 Ocak 2020 Dergi makalesi Açık Erişim

Specia, Lucia; Barrault, Loic; Caglayan, Ozan; Duarte, Amanda; Elliott, Desmond; Gella, Spandana; Holzenberger, Nils; Lala, Chiraag; Lee, Sun Jae; Libovicky, Jindrich; Madhyastha, Pranava; Metze, Florian; Mulligan, Karl; Ostapenko, Alissa; Palaskar, Shruti; Sanabria, Ramon; Wang, Josiah; Arora, Raman

JSON-LD (schema.org)

{
  "@context": "https://schema.org/", 
  "@id": 5905, 
  "@type": "ScholarlyArticle", 
  "creator": [
    {
      "@type": "Person", 
      "name": "Specia, Lucia"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Univ Sheffield, Dept Comp Sci, Sheffield S10 2TG, S Yorkshire, England", 
      "name": "Barrault, Loic"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Imperial Coll London, Dept Comp, London SW7 2BU, England", 
      "name": "Caglayan, Ozan"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Univ Politcn Catalunya, Dept Signal Theory & Commun, Barcelona 08034, Spain", 
      "name": "Duarte, Amanda"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Univ Copenhagen, Dept Comp Sci, DK-1165 Copenhagen, Denmark", 
      "name": "Elliott, Desmond"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Univ Edinburgh, Inst Language Cognit & Computat, Edinburgh EH8 9YL, Midlothian, Scotland", 
      "name": "Gella, Spandana"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Johns Hopkins Univ, Ctr Language & Speech Proc, Baltimore, MD 21218 USA", 
      "name": "Holzenberger, Nils"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Univ Sheffield, Dept Comp Sci, Sheffield S10 2TG, S Yorkshire, England", 
      "name": "Lala, Chiraag"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Univ Penn, Philadelphia, PA 19104 USA", 
      "name": "Lee, Sun Jae"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Ludwig Maximilians Univ Munchen, Ctr Informat & Language Proc, D-80333 Munich, Germany", 
      "name": "Libovicky, Jindrich"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Imperial Coll London, Dept Comp, London SW7 2BU, England", 
      "name": "Madhyastha, Pranava"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Carnegie Mellon Univ, Language Technol Inst, Pittsburgh, PA 15213 USA", 
      "name": "Metze, Florian"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Johns Hopkins Univ, Baltimore, MD 21218 USA", 
      "name": "Mulligan, Karl"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Worcester Polytech Inst, Worcester, MA 01609 USA", 
      "name": "Ostapenko, Alissa"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Carnegie Mellon Univ, Language Technol Inst, Pittsburgh, PA 15213 USA", 
      "name": "Palaskar, Shruti"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Carnegie Mellon Univ, Language Technol Inst, Pittsburgh, PA 15213 USA", 
      "name": "Sanabria, Ramon"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Imperial Coll London, Dept Comp, London SW7 2BU, England", 
      "name": "Wang, Josiah"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Johns Hopkins Univ, Ctr Language & Speech Proc, Baltimore, MD 21218 USA", 
      "name": "Arora, Raman"
    }
  ], 
  "datePublished": "2020-01-01", 
  "description": "Speech recognition and machine translation have made major progress over the past decades, providing practical systems to map one language sequence to another. Although multiple modalities such as sound and video are becoming increasingly available, the state-of-the-art systems are inherently unimodal, in the sense that they take a single modality - either speech or text - as input. Evidence from human learning suggests that additional modalities can provide disambiguating signals crucial for many language tasks. In this article, we describe the How2 dataset , a large, open-domain collection of videos with transcriptions and their translations. We then show how this single dataset can be used to develop systems for a variety of language tasks and present a number of models meant as starting points. Across tasks, we find that building multimodal architectures that perform better than their unimodal counterpart remains a challenge. This leaves plenty of room for the exploration of more advanced solutions that fully exploit the multimodal nature of the How2 dataset , and the general direction of multimodal learning with other datasets as well.", 
  "headline": "Grounded Sequence to Sequence Transduction", 
  "identifier": 5905, 
  "image": "https://aperta.ulakbim.gov.tr/static/img/logo/aperta_logo_with_icon.svg", 
  "license": "http://www.opendefinition.org/licenses/cc-by", 
  "name": "Grounded Sequence to Sequence Transduction", 
  "url": "https://aperta.ulakbim.gov.tr/record/5905"
}