<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=Windows-1252">
<style type="text/css" style="display:none;"> P {margin-top:0;margin-bottom:0;} </style>
</head>
<body dir="ltr">
<div style="font-family: Calibri, Arial, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
Hi everyone,</div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
We'll be discussing the following paper in CaCL next week:</div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<a href="https://www.aclweb.org/anthology/P19-1507/" id="LPlnk260051">https://www.aclweb.org/anthology/P19-1507/</a><br>
</div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<span><b><br>
</b></span></div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<span><b>Abstract</b><br>
</span><span>What is the relationship between sentence representations learned by deep recurrent models against those encoded by the brain? Is there any correspondence between hidden layers of these recurrent models and brain regions when processing sentences?
Can these deep models be used to synthesize brain data which can then be utilized in other extrinsic tasks? We investigate these questions using sentences with simple syntax and semantics (e.g., The bone was eaten by the dog.). We consider multiple neural
network architectures, including recently proposed ELMo and BERT. We use magnetoencephalography (MEG) brain recording data collected from human subjects when they were reading these simple sentences. Overall, we find that BERT’s activations correlate the best
with MEG brain data. We also find that the deep network representation can be used to generate brain data from new sentences to augment existing brain data. To the best of our knowledge, this is the first work showing that the MEG brain recording when reading
a word in a sentence can be used to distinguish earlier words in the sentence. Our exploration is also the first to use deep neural network representations to generate synthetic brain data and to show that it helps in improving subsequent stimuli decoding
task accuracy.</span><br>
</div>
<div id="LPBorder_GTaHR0cHM6Ly93d3cuYWNsd2ViLm9yZy9hbnRob2xvZ3kvUDE5LTE1MDcv" class="LPBorder205059" contenteditable="false" style="width: 100%; margin-top: 16px; margin-bottom: 16px; position: relative; max-width: 800px; min-width: 424px;">
<table id="LPContainer205059" role="presentation" style="padding: 12px 36px 12px 12px; width: 100%; border-width: 1px; border-style: solid; border-color: rgb(200, 200, 200); border-radius: 2px;">
<tbody>
<tr valign="top" style="border-spacing: 0px;">
<td style="width: 100%;">
<div id="LPTitle205059" style="font-size: 21px; font-weight: 300; margin-right: 8px; font-family: wf_segoe-ui_light, "Segoe UI Light", "Segoe WP Light", "Segoe UI", "Segoe WP", Tahoma, Arial, sans-serif; margin-bottom: 12px;">
<a target="_blank" id="LPUrlAnchor205059" href="https://www.aclweb.org/anthology/P19-1507/" style="text-decoration: none; color: var(--themePrimary);">Relating Simple Sentence Representations in Deep Neural Networks and the Brain - aclweb.org</a></div>
<div id="LPDescription205059" style="font-size: 14px; max-height: 100px; color: rgb(102, 102, 102); font-family: wf_segoe-ui_normal, "Segoe UI", "Segoe WP", Tahoma, Arial, sans-serif; margin-bottom: 12px; margin-right: 8px; overflow: hidden;">
5140 multitask model is a simple two layer bidi-rectional LSTM model with separate linear layers predicting each of the tasks given the output of the last LSTM layer (Figure2).</div>
<div id="LPMetadata205059" style="font-size: 14px; font-weight: 400; color: rgb(166, 166, 166); font-family: wf_segoe-ui_normal, "Segoe UI", "Segoe WP", Tahoma, Arial, sans-serif;">
www.aclweb.org</div>
</td>
</tr>
</tbody>
</table>
</div>
<div id="Signature">
<div></div>
<div></div>
<div style="font-family:Calibri,Arial,Helvetica,sans-serif; font-size:12pt; color:rgb(0,0,0)">
<span style="font-family:"Lucida Sans Unicode","Lucida Grande",sans-serif; font-size:10pt">=================</span></div>
<div style="font-family:Calibri,Arial,Helvetica,sans-serif; font-size:12pt; color:rgb(0,0,0)">
<span style="font-size:10pt"></span><span style="font-size:11pt"></span><span style="font-family:"Lucida Sans Unicode","Lucida Grande",sans-serif; font-size:10pt"><b>Byung-Doh Oh</b></span></div>
<div style="font-family:Calibri,Arial,Helvetica,sans-serif; font-size:12pt; color:rgb(0,0,0)">
<span style="font-size:10pt"></span><span style="font-size:11pt"></span><span style="font-family:"Lucida Sans Unicode","Lucida Grande",sans-serif; font-size:10pt">Ph.D. Student</span></div>
<div style="font-family:Calibri,Arial,Helvetica,sans-serif; font-size:12pt; color:rgb(0,0,0)">
<span style="font-size:10pt"></span><span style="font-size:11pt"></span><span style="font-family:"Lucida Sans Unicode","Lucida Grande",sans-serif; font-size:10pt">Department of Linguistics</span></div>
<div style="font-family:Calibri,Arial,Helvetica,sans-serif; font-size:12pt; color:rgb(0,0,0)">
<span style="font-size:10pt"></span><span style="font-size:11pt"></span><span style="font-family:"Lucida Sans Unicode","Lucida Grande",sans-serif; font-size:10pt">The Ohio State University</span></div>
<div style="font-family:Calibri,Arial,Helvetica,sans-serif; font-size:12pt; color:rgb(0,0,0)">
<span style="font-size:10pt"></span><span style="font-size:11pt"></span><a href="https://byungdoh.github.io"><span style="font-family:"Lucida Sans Unicode","Lucida Grande",sans-serif; font-size:10pt">https://byungdoh.github.io</span></a><br>
</div>
</div>
</body>
</html>