<!DOCTYPE html>
<html class="client-nojs vector-feature-night-mode-disabled vector-feature-language-in-header-enabled vector-feature-language-in-main-page-header-disabled vector-feature-page-tools-pinned-disabled vector-feature-toc-pinned-clientpref-1 vector-feature-main-menu-pinned-disabled vector-feature-limited-width-clientpref-1 vector-feature-limited-width-content-enabled vector-feature-custom-font-size-clientpref-1 vector-feature-appearance-pinned-clientpref-1 vector-sticky-header-enabled" lang="en" dir="ltr"><head>
<meta charset="UTF-8">
<title>Never-Ending Language Learning</title>
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<link rel="canonical" href="https://en.wikipedia.org/wiki/Never-Ending_Language_Learning"> <link href="./mw/ext.cite.styles.css" rel="stylesheet" type="text/css">
<link href="./mw/skins.vector.icons.css" rel="stylesheet" type="text/css">
<link href="./mw/skins.vector.search.codex.styles.css" rel="stylesheet" type="text/css">
<link href="./mw/skins.vector.styles.css" rel="stylesheet" type="text/css">
<link href="./mw/user.styles.css" rel="stylesheet" type="text/css">
<meta name="ResourceLoaderDynamicStyles" content="">
<link rel="stylesheet" type="text/css" href="./mw/site.styles.css">
<link rel="stylesheet" type="text/css" href="./mw/noscript.css">
<link rel="stylesheet" type="text/css" href="./footer.css">
<link rel="stylesheet" type="text/css" href="./vector-2022.css">
</head>
<body class="skin--responsive skin-vector skin-vector-search-vue mediawiki ltr sitedir-ltr mw-hide-empty-elt ns-0 ns-subject page-Never-Ending_Language_Learning rootpage-Never-Ending_Language_Learning skin-vector-2022 action-view">
<div class="mw-page-container">
<div class="mw-page-container-inner">
<div class="mw-content-container">
<main id="content" class="mw-body">
<header class="mw-body-header vector-page-titlebar">
<h1 id="firstHeading" class="firstHeading mw-first-heading">
<span id="openzim-page-title" class="mw-page-title-main"><span class="mw-page-title-main">Never-Ending Language Learning</span></span>
</h1>
</header>
<a id="top"></a>
<div id="bodyContent" class="vector-body ve-init-mw-desktopArticleTarget-targetContainer" aria-labelledby="firstHeading" data-mw-ve-target-container="">
<div id="mw-content-text" class="mw-body-content mw-content-ltr" lang="en" dir="ltr"><div class="mw-content-ltr mw-parser-output" lang="en" dir="ltr"><style data-mw-deduplicate="TemplateStyles:r1236090951">
/* start https://en.wikipedia.org/ */
.mw-parser-output .hatnote{font-style:italic}.mw-parser-output div.hatnote{padding-left:1.6em;margin-bottom:0.5em}.mw-parser-output .hatnote i{font-style:normal}.mw-parser-output .hatnote+link+.hatnote{margin-top:-0.5em}@media print{body.ns-0 .mw-parser-output .hatnote{display:none!important}}
/* end https://en.wikipedia.org/ */
</style><div role="note" class="hatnote navigation-not-searchable">"NELL" redirects here. For other uses, see <a href="Nell" title="Nell">Nell</a>.</div>
<p><b>Never-Ending Language Learning</b> system (<b>NELL</b>) is a <a href="Semantics" title="Semantics">semantic</a> <a href="Machine_learning" title="Machine learning">machine learning</a> <a href="Computer_system" class="mw-redirect" title="Computer system">system</a> that as of 2010 was being developed by a research team at <a href="Carnegie_Mellon_University" title="Carnegie Mellon University">Carnegie Mellon University</a>, and supported by grants from <a href="DARPA" title="DARPA">DARPA</a>, <a href="Google" title="Google">Google</a>, <a href="National_Science_Foundation" title="National Science Foundation">NSF</a>, and <a href="CNPq" class="mw-redirect" title="CNPq">CNPq</a> with portions of the system running on a <a href="Supercomputer" title="Supercomputer">supercomputing</a> <a href="Computer_cluster" title="Computer cluster">cluster</a> provided by <a href="Yahoo!" class="mw-redirect" title="Yahoo!">Yahoo!</a>.<sup id="cite_ref-NYT2010_1-0" class="reference"><a href="#cite_note-NYT2010-1"><span class="cite-bracket">[</span>1<span class="cite-bracket">]</span></a></sup>
</p>
<meta property="mw:PageProp/toc">
<div class="mw-heading mw-heading2"><h2 id="Process_and_goals">Process and goals</h2></div>
<style data-mw-deduplicate="TemplateStyles:r1251242444">
/* start https://en.wikipedia.org/ */
.mw-parser-output .ambox{border:1px solid #a2a9b1;border-left:10px solid #36c;background-color:#fbfbfb;box-sizing:border-box}.mw-parser-output .ambox+link+.ambox,.mw-parser-output .ambox+link+style+.ambox,.mw-parser-output .ambox+link+link+.ambox,.mw-parser-output .ambox+.mw-empty-elt+link+.ambox,.mw-parser-output .ambox+.mw-empty-elt+link+style+.ambox,.mw-parser-output .ambox+.mw-empty-elt+link+link+.ambox{margin-top:-1px}html body.mediawiki .mw-parser-output .ambox.mbox-small-left{margin:4px 1em 4px 0;overflow:hidden;width:238px;border-collapse:collapse;font-size:88%;line-height:1.25em}.mw-parser-output .ambox-speedy{border-left:10px solid #b32424;background-color:#fee7e6}.mw-parser-output .ambox-delete{border-left:10px solid #b32424}.mw-parser-output .ambox-content{border-left:10px solid #f28500}.mw-parser-output .ambox-style{border-left:10px solid #fc3}.mw-parser-output .ambox-move{border-left:10px solid #9932cc}.mw-parser-output .ambox-protection{border-left:10px solid #a2a9b1}.mw-parser-output .ambox .mbox-text{border:none;padding:0.25em 0.5em;width:100%}.mw-parser-output .ambox .mbox-image{border:none;padding:2px 0 2px 0.5em;text-align:center}.mw-parser-output .ambox .mbox-imageright{border:none;padding:2px 0.5em 2px 0;text-align:center}.mw-parser-output .ambox .mbox-empty-cell{border:none;padding:0;width:1px}.mw-parser-output .ambox .mbox-image-div{width:52px}@media(min-width:720px){.mw-parser-output .ambox{margin:0 10%}}@media print{body.ns-0 .mw-parser-output .ambox{display:none!important}}
/* end https://en.wikipedia.org/ */
</style>
<p>NELL was programmed by its developers to be able to identify a basic set of fundamental semantic relationships between a few hundred predefined categories of data, such as cities, companies, emotions and sports teams. Since the beginning of 2010, the Carnegie Mellon research team has been running NELL around the clock, sifting through hundreds of millions of web pages looking for connections between the information it already knows and what it finds through its search process – to make new connections in a manner that is intended to mimic the way humans learn new information.<sup id="cite_ref-2" class="reference"><a href="#cite_note-2"><span class="cite-bracket">[</span>2<span class="cite-bracket">]</span></a></sup> For example, in encountering the word pair "Pikes Peak", NELL would notice that both words are capitalized and deduce from the second word that it was the name of a mountain, and then build on the relationship of words surrounding those two words to deduce other connections.<sup id="cite_ref-NYT2010_1-1" class="reference"><a href="#cite_note-NYT2010-1"><span class="cite-bracket">[</span>1<span class="cite-bracket">]</span></a></sup>
</p><p>The goal of NELL and other semantic learning systems, such as <a href="IBM" title="IBM">IBM</a>'s <a href="Watson_(artificial_intelligence_software)" class="mw-redirect" title="Watson (artificial intelligence software)">Watson</a> system, is to be able to develop means of <a href="Question_answering" title="Question answering">answering questions</a> posed by users in natural language with no human intervention in the process.<sup id="cite_ref-3" class="reference"><a href="#cite_note-3"><span class="cite-bracket">[</span>3<span class="cite-bracket">]</span></a></sup> <a href="Oren_Etzioni" title="Oren Etzioni">Oren Etzioni</a> of the <a href="University_of_Washington" title="University of Washington">University of Washington</a> lauded the system's "continuous learning, as if NELL is exercising curiosity on its own, with little human help".<sup id="cite_ref-NYT2010_1-2" class="reference"><a href="#cite_note-NYT2010-1"><span class="cite-bracket">[</span>1<span class="cite-bracket">]</span></a></sup>
</p><p>By October 2010, NELL has doubled the number of relationships it has available in its knowledge base and has learned 440,000 new facts, with an accuracy of 87%.<sup id="cite_ref-4" class="reference"><a href="#cite_note-4"><span class="cite-bracket">[</span>4<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-NYT2010_1-3" class="reference"><a href="#cite_note-NYT2010-1"><span class="cite-bracket">[</span>1<span class="cite-bracket">]</span></a></sup> Team leader <a href="Tom_M._Mitchell" title="Tom M. Mitchell">Tom M. Mitchell</a>, chairman of the machine learning department at Carnegie Mellon described how NELL "self-corrects when it has more information, as it learns more", though it does sometimes arrive at incorrect conclusions. Accumulated errors, such as the deduction that <a href="HTTP_cookie" title="HTTP cookie">Internet cookies</a> were a kind of baked good, led NELL to deduce from the phrases "I deleted my Internet cookies" and "I deleted my files" that "<a href="Computer_file" title="Computer file">computer files</a>" also belonged in the baked goods category.<sup id="cite_ref-5" class="reference"><a href="#cite_note-5"><span class="cite-bracket">[</span>5<span class="cite-bracket">]</span></a></sup> Clear errors like these are corrected every few weeks by the members of the research team and the system is allowed to continue its learning process.<sup id="cite_ref-NYT2010_1-4" class="reference"><a href="#cite_note-NYT2010-1"><span class="cite-bracket">[</span>1<span class="cite-bracket">]</span></a></sup> By 2018, NELL had "acquired a knowledge base with 120mn diverse, confidence-weighted beliefs (e.g., <i>servedWith(tea,biscuits)</i>), while learning thousands of interrelated functions that continually improve its reading competence over time."<sup id="cite_ref-6" class="reference"><a href="#cite_note-6"><span class="cite-bracket">[</span>6<span class="cite-bracket">]</span></a></sup>
</p><p>As of September 2023, the project's most recently gathered facts dated from February 2019 (according to its Twitter feed)<sup id="cite_ref-7" class="reference"><a href="#cite_note-7"><span class="cite-bracket">[</span>7<span class="cite-bracket">]</span></a></sup> or September 2018 (according to its home page).<sup id="cite_ref-8" class="reference"><a href="#cite_note-8"><span class="cite-bracket">[</span>8<span class="cite-bracket">]</span></a></sup>
</p>
<div class="mw-heading mw-heading2"><h2 id="Reception">Reception</h2></div>
<p>In his 2019 book "<a href="Human_Compatible" title="Human Compatible">Human Compatible</a>", <a href="Stuart_J._Russell" title="Stuart J. Russell">Stuart Russell</a> commented that 'Unfortunately NELL has confidence in only 3 percent of its beliefs and relies on human experts to clean out false or meaningless beliefs on a regular basis—such as its beliefs that “Nepal is a country also known as United States” and "value is an agricultural product that is usually cut into basis."'<sup id="cite_ref-9" class="reference"><a href="#cite_note-9"><span class="cite-bracket">[</span>9<span class="cite-bracket">]</span></a></sup> A 2023 paper commented that "While the <i>never-ending</i> part seems like the right approach, NELL still had the drawback that its focus remained much too grounded on object-language descriptions, and relied on web pages as its only source, which significantly influenced the type of grammar, symbolism, slang, etc. analysed."<sup id="cite_ref-10" class="reference"><a href="#cite_note-10"><span class="cite-bracket">[</span>10<span class="cite-bracket">]</span></a></sup>
</p>
<div class="mw-heading mw-heading2"><h2 id="See_also">See also</h2></div>
<ul><li><a href="Cognitive_architecture" title="Cognitive architecture">Cognitive architecture</a></li>
<li><a href="Computational_models_of_language_acquisition" class="mw-redirect" title="Computational models of language acquisition">Computational models of language acquisition</a></li>
<li><a href="Cyc" title="Cyc">Cyc</a></li>
<li><a href="Darwin_among_the_Machines" title="Darwin among the Machines">Darwin among the Machines</a></li>
<li><a href="The_Adolescence_of_P-1" title="The Adolescence of P-1">The Adolescence of P-1</a></li></ul>
<div class="mw-heading mw-heading2"><h2 id="References">References</h2></div>
<style data-mw-deduplicate="TemplateStyles:r1239543626">
/* start https://en.wikipedia.org/ */
.mw-parser-output .reflist{margin-bottom:0.5em;list-style-type:decimal}@media screen{.mw-parser-output .reflist{font-size:90%}}.mw-parser-output .reflist .references{font-size:100%;margin-bottom:0;list-style-type:inherit}.mw-parser-output .reflist-columns-2{column-width:30em}.mw-parser-output .reflist-columns-3{column-width:25em}.mw-parser-output .reflist-columns{margin-top:0.3em}.mw-parser-output .reflist-columns ol{margin-top:0}.mw-parser-output .reflist-columns li{page-break-inside:avoid;break-inside:avoid-column}.mw-parser-output .reflist-upper-alpha{list-style-type:upper-alpha}.mw-parser-output .reflist-upper-roman{list-style-type:upper-roman}.mw-parser-output .reflist-lower-alpha{list-style-type:lower-alpha}.mw-parser-output .reflist-lower-greek{list-style-type:lower-greek}.mw-parser-output .reflist-lower-roman{list-style-type:lower-roman}
/* end https://en.wikipedia.org/ */
</style><div class="reflist">
<div class="mw-references-wrap"><ol class="references">
<li id="cite_note-NYT2010-1"><span class="mw-cite-backlink">^ <a href="#cite_ref-NYT2010_1-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-NYT2010_1-1"><sup><i><b>b</b></i></sup></a> <a href="#cite_ref-NYT2010_1-2"><sup><i><b>c</b></i></sup></a> <a href="#cite_ref-NYT2010_1-3"><sup><i><b>d</b></i></sup></a> <a href="#cite_ref-NYT2010_1-4"><sup><i><b>e</b></i></sup></a></span> <span class="reference-text"><style data-mw-deduplicate="TemplateStyles:r1238218222">
/* start https://en.wikipedia.org/ */
.mw-parser-output cite.citation{font-style:inherit;word-wrap:break-word}.mw-parser-output .citation q{quotes:"\"""\"""'""'"}.mw-parser-output .citation:target{background-color:rgba(0,127,255,0.133)}.mw-parser-output .id-lock-free.id-lock-free a{background:url("./mw/Lock-green.svg")right 0.1em center/9px no-repeat}.mw-parser-output .id-lock-limited.id-lock-limited a,.mw-parser-output .id-lock-registration.id-lock-registration a{background:url("./mw/Lock-gray-alt-2.svg")right 0.1em center/9px no-repeat}.mw-parser-output .id-lock-subscription.id-lock-subscription a{background:url("./mw/Lock-red-alt-2.svg")right 0.1em center/9px no-repeat}.mw-parser-output .cs1-ws-icon a{background:url("./mw/Wikisource-logo.svg")right 0.1em center/12px no-repeat}body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .id-lock-free a,body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .id-lock-limited a,body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .id-lock-registration a,body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .id-lock-subscription a,body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .cs1-ws-icon a{background-size:contain;padding:0 1em 0 0}.mw-parser-output .cs1-code{color:inherit;background:inherit;border:none;padding:inherit}.mw-parser-output .cs1-hidden-error{display:none;color:var(--color-error,#d33)}.mw-parser-output .cs1-visible-error{color:var(--color-error,#d33)}.mw-parser-output .cs1-maint{display:none;color:#085;margin-left:0.3em}.mw-parser-output .cs1-kern-left{padding-left:0.2em}.mw-parser-output .cs1-kern-right{padding-right:0.2em}.mw-parser-output .citation .mw-selflink{font-weight:inherit}@media screen{.mw-parser-output .cs1-format{font-size:95%}html.skin-theme-clientpref-night .mw-parser-output .cs1-maint{color:#18911f}}@media screen and (prefers-color-scheme:dark){html.skin-theme-clientpref-os .mw-parser-output .cs1-maint{color:#18911f}}
/* end https://en.wikipedia.org/ */
</style><cite class="citation news cs1"><a rel="nofollow" class="external text" href="https://www.nytimes.com/2010/10/05/science/05compute.html?hpw=&pagewanted=all">"Aiming to Learn as We Do, a Machine Teaches Itself"</a>. <i><a href="New_York_Times" class="mw-redirect" title="New York Times">New York Times</a></i>. October 4, 2010<span class="reference-accessdate">. Retrieved <span class="nowrap">2010-10-05</span></span>. <q>Since the start of the year, a team of researchers at Carnegie Mellon University — supported by grants from the Defense Advanced Research Projects Agency and Google, and tapping into a research supercomputing cluster provided by Yahoo — has been fine-tuning a computer system that is trying to master semantics by learning more like a human.</q></cite></span>
</li>
<li id="cite_note-2"><span class="mw-cite-backlink"><b><a href="#cite_ref-2">^</a></b></span> <span class="reference-text"><a rel="nofollow" class="external text" href="http://rtw.ml.cmu.edu/rtw/overview">Project Overview</a>, <a href="Carnegie_Mellon_University" title="Carnegie Mellon University">Carnegie Mellon University</a>. Accessed October 5, 2010.</span>
</li>
<li id="cite_note-3"><span class="mw-cite-backlink"><b><a href="#cite_ref-3">^</a></b></span> <span class="reference-text">Trader, Tiffany. <a rel="nofollow" class="external text" href="http://www.hpcwire.com/news/Machine-Learns-Language-Starting-with-the-Facts-104384244.html">"Machine Learns Language Starting with the Facts"</a>, HPCwire, October 5, 2010. Accessed October 5, 2010.</span>
</li>
<li id="cite_note-4"><span class="mw-cite-backlink"><b><a href="#cite_ref-4">^</a></b></span> <span class="reference-text"><a rel="nofollow" class="external text" href="http://rtw.ml.cmu.edu/rtw/">"NELL: Never-Ending Language Learning"</a>, <a href="Carnegie_Mellon_University" title="Carnegie Mellon University">Carnegie Mellon University</a>. Accessed October 5, 2010.</span>
</li>
<li id="cite_note-5"><span class="mw-cite-backlink"><b><a href="#cite_ref-5">^</a></b></span> <span class="reference-text">VanHemert, Kyle. <a rel="nofollow" class="external text" href="http://www.gizmodo.com.au/2010/10/right-now-a-computer-is-reading-online-teaching-itself-language/">"Right Now A Computer Is Reading Online, Teaching Itself Language"</a>, <a href="Gizmodo" title="Gizmodo">Gizmodo</a>, October 6, 2010. Accessed October 5, 2010.</span>
</li>
<li id="cite_note-6"><span class="mw-cite-backlink"><b><a href="#cite_ref-6">^</a></b></span> <span class="reference-text"><cite id="CITEREFMitchellCohenHruschkaTalukdar2018" class="citation journal cs1">Mitchell, T.; Cohen, W.; Hruschka, E.; Talukdar, P.; Yang, B.; Betteridge, J.; Carlson, A.; Dalvi, B.; Gardner, M.; Kisiel, B.; Krishnamurthy, J.; Lao, N.; Mazaitis, K.; Mohamed, T.; Nakashole, N. (2018-04-24). <a rel="nofollow" class="external text" href="https://doi.org/10.1145%2F3191513">"Never-ending learning"</a>. <i>Communications of the ACM</i>. <b>61</b> (5): <span class="nowrap">103–</span>115. <a href="Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<span class="id-lock-free" title="Freely accessible"><a rel="nofollow" class="external text" href="https://doi.org/10.1145%2F3191513">10.1145/3191513</a></span>. <a href="ISSN_(identifier)" class="mw-redirect" title="ISSN (identifier)">ISSN</a> <a rel="nofollow" class="external text" href="https://search.worldcat.org/issn/0001-0782">0001-0782</a>.</cite></span>
</li>
<li id="cite_note-7"><span class="mw-cite-backlink"><b><a href="#cite_ref-7">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://twitter.com/cmunell">"NELL (@cmunell) | Twitter"</a>. <i>twitter.com</i><span class="reference-accessdate">. Retrieved <span class="nowrap">2023-09-04</span></span>.</cite></span>
</li>
<li id="cite_note-8"><span class="mw-cite-backlink"><b><a href="#cite_ref-8">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="http://rtw.ml.cmu.edu/rtw/">"Read the Web :: Carnegie Mellon University"</a>. <i>rtw.ml.cmu.edu</i><span class="reference-accessdate">. Retrieved <span class="nowrap">2023-09-04</span></span>.</cite></span>
</li>
<li id="cite_note-9"><span class="mw-cite-backlink"><b><a href="#cite_ref-9">^</a></b></span> <span class="reference-text"><cite id="CITEREFRussell2019" class="citation book cs1">Russell, Stuart (2019). "3". <i>Human Compatible: AI and the Problem of Control</i>. Allen Lane.</cite></span>
</li>
<li id="cite_note-10"><span class="mw-cite-backlink"><b><a href="#cite_ref-10">^</a></b></span> <span class="reference-text"><cite id="CITEREFde_Jager2023" class="citation journal cs1">de Jager, S. (2023-04-11). <a rel="nofollow" class="external text" href="https://doi.org/10.1057%2Fs41599-023-01643-9">"Semantic noise in the Winograd Schema Challenge of pronoun disambiguation"</a>. <i>Humanities and Social Sciences Communications</i>. <b>10</b> (1): <span class="nowrap">1–</span>10. <a href="Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<span class="id-lock-free" title="Freely accessible"><a rel="nofollow" class="external text" href="https://doi.org/10.1057%2Fs41599-023-01643-9">10.1057/s41599-023-01643-9</a></span>. <a href="ISSN_(identifier)" class="mw-redirect" title="ISSN (identifier)">ISSN</a> <a rel="nofollow" class="external text" href="https://search.worldcat.org/issn/2662-9992">2662-9992</a>.</cite></span>
</li>
</ol></div></div>
<div class="mw-heading mw-heading2"><h2 id="External_links">External links</h2></div>
<ul><li><a rel="nofollow" class="external text" href="http://rtw.ml.cmu.edu/rtw/">Project homepage</a></li></ul></div><!--htdig_noindex--><div><div class="zim-footer">
This article is issued from <a class="external text" title="Last edited on 2025-04-13" href="https://en.wikipedia.org/wiki/?title=Never-Ending_Language_Learning&oldid=1285343838">Wikipedia</a>. The text is available under <a class="external text" href="https://creativecommons.org/licenses/by-sa/4.0/deed.en">Creative Commons Attribution-Share Alike 4.0</a> unless otherwise noted. Additional terms may apply for the media files.
</div>
</div><!--/htdig_noindex--></div>
</div>
</main>
</div>
</div>
</div>
</body></html>