<html xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<meta name="Generator" content="Microsoft Word 15 (filtered medium)">
<style><!--
/* Font Definitions */
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
@font-face
{font-family:-webkit-standard;
panose-1:2 11 6 4 2 2 2 2 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0in;
margin-bottom:.0001pt;
font-size:12.0pt;
font-family:"Calibri",sans-serif;}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:#0563C1;
text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
{mso-style-priority:99;
color:#954F72;
text-decoration:underline;}
span.EmailStyle17
{mso-style-type:personal-compose;
font-family:"Calibri",sans-serif;
color:windowtext;}
span.apple-converted-space
{mso-style-name:apple-converted-space;}
.MsoChpDefault
{mso-style-type:export-only;
font-family:"Calibri",sans-serif;}
@page WordSection1
{size:8.5in 11.0in;
margin:1.0in 1.0in 1.0in 1.0in;}
div.WordSection1
{page:WordSection1;}
--></style>
</head>
<body lang="EN-US" link="#0563C1" vlink="#954F72">
<div class="WordSection1">
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black">EMNLP 2018 Workshop: Analyzing and interpreting neural networks for NLP<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black"><a href="https://blackboxnlp.github.io/">https://blackboxnlp.github.io/</a><o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black">Call for papers<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black">===============<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black">Neural networks have rapidly become a central component in language and speech understanding systems in the last few years. The improvements in accuracy and performance brought
by the introduction of neural networks has typically come at the cost of our understanding of the system: what are the representations and computations that the network learns? The goal of this workshop is to bring together people who are attempting to peek
inside the neural network black box, taking inspiration from machine learning, psychology, linguistics and neuroscience. The topics of the workshop will include, but are not limited to:<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black">- Applying analysis techniques from neuroscience to analyze high-dimensional vector representations (such as Haxby et al., 2001; Kriegeskorte, 2008) in artificial neural networks;<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black">- Analyzing the network’s response to strategically chosen inputs in order to infer the linguistic generalizations that the network has acquired (e.g., Linzen et al., 2016);<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black">- Examining the performance of the network on simplified or formal languages;<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black">- Proposing modifications to neural network architectures that can make them more interpretable (e.g., Palangi et al., 2017);<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black">- Scaling up neural network analysis techniques developed in the connectionist literature in the 1990s (Elman, 1991);<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black">- Testing whether interpretable information can be decoded from intermediate representations (e.g., Adi et al., 2017; Chrupała et al., 2017);<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black">- Translating insights on neural network interpretation from the vision domain (e.g., Zeiler & Fergus, 2014) to language.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black">Important dates<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black">===============<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black">July 13: Submission deadline.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black">August 3: Notification of acceptance.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black">October 31 or November 1: Workshop.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black">Submission types<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black">================<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black">- Archival papers. These are papers reporting on completed, original and unpublished research, with maximum length of 8 pages + references. Papers shorter than this maximum
are also welcome. Accepted papers are expected to be presented at the workshop and will be published in the workshop proceedings. They should report on obtained results rather than intended work. These papers will undergo double-blind peer-review, and should
thus be anonymized.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black">- Extended abstracts. These may report on work in progress or may be cross submissions that have already appeared in a non-NLP venue. The extended abstracts are of maximum 2
pages + references. These submissions are non-archival in order to allow submission to another venue. The selection will not be based on a double-blind review and thus submissions of this type need not be anonymized.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black">Both categories of submissions should use EMNLP 2018 templates:<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black">- Latex:<span class="apple-converted-space"> </span><a href="http://emnlp2018.org/downloads/emnlp18-latex.zip">http://emnlp2018.org/downloads/emnlp18-latex.zip</a><o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black">- Word:<span class="apple-converted-space"> </span><a href="http://emnlp2018.org/downloads/emnlp18-word.zip">http://emnlp2018.org/downloads/emnlp18-word.zip</a> <o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black">Papers and abstracts should be submitted via softconf:<span class="apple-converted-space"> </span><a href="https://www.softconf.com/emnlp2018/BlackboxNLP/">https://www.softconf.com/emnlp2018/BlackboxNLP/</a><o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black">Workshop organizers<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black">===================<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black">Tal Linzen, Johns Hopkins University (<a href="mailto:tal.linzen@jhu.edu">tal.linzen@jhu.edu</a>)<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black">Afra Alishahi, Tilburg University (<a href="mailto:a.alishahi@uvt.nl">a.alishahi@uvt.nl</a>)<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"-webkit-standard",serif;color:black">Grzegorz Chrupała, Tilburg University (<a href="mailto:g.a.chrupala@uvt.nl">g.a.chrupala@uvt.nl</a>)<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt"><o:p> </o:p></span></p>
</div>
</body>
</html>