data.html

---
layout: default
nav_active: data
title: Webis Data
description: Overview of corpora that are used by the Webis
---
<nav class="uk-container">
<ul class="uk-breadcrumb">
<li><a href="index.html">Webis.de</a></li>
<li class="uk-disabled"><a href="#">Data</a></li>
</ul>
</nav>

<script type="application/ld+json">
    {
        "@context": "http://schema.org/",
        "@type": "DataCatalog",
        "name": "Webis Data",
        "description": "Overview of corpora that are used by the Webis research group.",
        "url": "https://webis.de/data.html",
        "keywords": [
            "webis",
            "data",
            "corpora",
            "corpus"
        ],
        "author": [
            {
                "@type": "Organization",
                "url": "https://webis.de/",
                "name": "The Web Technology & Information Systems Network",
                "alternateName": "Webis"
            }
        ]
    }
</script>

<main class="uk-section uk-section-default">
<div class="uk-container">
    <h1>Data</h1>

    <ul class="uk-list">
        <li><span data-uk-icon="chevron-down"></span> <a href="#released-webis-corpora">Released Webis Corpora</a>
        </li>
        <li><span data-uk-icon="chevron-down"></span> <a href="#pan-corpora">PAN Corpora</a></li>
        <li><span data-uk-icon="chevron-down"></span> <a href="#touche-corpora">Touché Corpora</a></li>
        <li><span data-uk-icon="chevron-down"></span> <a href="#internal-webis-corpora">Internal Webis Corpora</a>
        </li>
        <li><span data-uk-icon="chevron-down"></span> <a href="#other-corpora">Other Corpora</a></li>
    </ul>
</div>

<div class="uk-container uk-margin-medium">
    <p>
        This page organizes all corpora which have resulted from or have been used in our research. Their availability for Webis externals is as follows:
        (1)&nbsp;corpora that have been officially released by Webis as well as
        (2)&nbsp;corpora of the PAN series can be downloaded here,
        (3)&nbsp;internal Webis corpora (which will be officially released in the future) are supplied upon request,
        (4)&nbsp;other corpora can be downloaded from their original publisher/creator.
        Most of our released corpora are hosted at <a title="Download: Zenodo" href="https://zenodo.org/communities/webis">Zenodo <img src="data/img/zenodo-icon.png" alt="(Zenodo)"></a> and are indexed in the <a title="Indexed: Google" href="https://toolbox.google.com/datasetsearch/search?query=webis-data-catalog">Google Dataset Search <img src="data/img/google-icon.png" alt="(Google Dataset Search)"></a>; a few larger corpora are available in the <a title="Internet Archive" href="https://archive.org/details/webis">Internet Archive <img src="data/img/ia-icon.png" alt="(Internet Archive)"></a>; some corpora are accessibly via the <a title="Hugging Face" href="https://huggingface.co/webis">Hugging Face <img src="data/img/huggingface-icon.png" alt="(Huggingface)"></a> and <a title="IR datasets" href="https://ir-datasets.com/index.html">IR datasets <img src="data/img/ir-icon.png" alt="(ir_datasets)"></a> libraries; the <img src="data/img/browser-icon-magnifier.png" alt="Browser"></a> &ndash;symbol indicates a browsing facility for the respective corpus.
    </p>

    <div id="search-control">
        <input type="text" class="uk-input" id="filter-field" placeholder="Type here to filter&hellip;"/>
    </div>
</div>

<div class="uk-container uk-margin-medium webis-data-table">
    {% include bib-data.html %}

    <div id="filtered-all-message" class="uk-hidden uk-text-muted" aria-hidden="true">
        None of our corpora match your filter.
    </div>
</div>
</main>

<script src="https://assets.webis.de/js/thirdparty/jquery/jquery.slim.min.js"></script>
<script src="https://assets.webis.de/js/thirdparty/fontawesome/fontawesome.min.js"></script>
<script src="https://assets.webis.de/js/thirdparty/fontawesome/solid.min.js"></script>
<script src="https://assets.webis.de/js/filter.js"></script>
<script src="https://assets.webis.de/js/selection.js"></script>
<script src="https://assets.webis.de/js/tables.js"></script>
<script>initWebisDataFiltering();</script>