Conference paper Open Access

KIT's Submission to the IWSLT 2019 Shared Task on Text Translation

Schneider, Felix; Waibel, Alex


JSON-LD (schema.org) Export

{
  "inLanguage": {
    "alternateName": "eng", 
    "@type": "Language", 
    "name": "English"
  }, 
  "description": "<p>In this paper, we describe KIT&rsquo;s submission for the IWSLT 2019 shared task on text translation. Our system is based on the transformer model [1] using our in-house implementation. We augment the available training data using back-translation and employ fine-tuning for the final model. For our best results, we used a 12-layer&nbsp;transformer-big&nbsp;config- uration, achieving state-of-the-art results on the WMT2018 test set. We also experiment with student-teacher models to improve performance of smaller models.</p>", 
  "license": "https://creativecommons.org/licenses/by/4.0/legalcode", 
  "creator": [
    {
      "affiliation": "Karlsruhe Institute of Technology", 
      "@type": "Person", 
      "name": "Schneider, Felix"
    }, 
    {
      "affiliation": "Karlsruhe Institute of Technology", 
      "@type": "Person", 
      "name": "Waibel, Alex"
    }
  ], 
  "headline": "KIT's Submission to the IWSLT 2019 Shared Task on Text Translation", 
  "image": "https://zenodo.org/static/img/logos/zenodo-gradient-round.svg", 
  "datePublished": "2019-11-02", 
  "url": "https://zenodo.org/record/3525496", 
  "@context": "https://schema.org/", 
  "identifier": "https://doi.org/10.5281/zenodo.3525496", 
  "@id": "https://doi.org/10.5281/zenodo.3525496", 
  "@type": "ScholarlyArticle", 
  "name": "KIT's Submission to the IWSLT 2019 Shared Task on Text Translation"
}
116
86
views
downloads
All versions This version
Views 116115
Downloads 8686
Data volume 8.2 MB8.2 MB
Unique views 102101
Unique downloads 8080

Share

Cite as