<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="Title" content="">
<meta name="Keywords" content="">
<meta name="Generator" content="Microsoft Word 15 (filtered medium)">
<style><!--
/* Font Definitions */
@font-face
{font-family:Arial;
panose-1:2 11 6 4 2 2 2 2 2 4;}
@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;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0in;
margin-bottom:.0001pt;
font-size:12.0pt;
font-family:Calibri;}
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;
color:windowtext;}
span.msoIns
{mso-style-type:export-only;
mso-style-name:"";
text-decoration:underline;
color:teal;}
.MsoChpDefault
{mso-style-type:export-only;
font-family:Calibri;}
@page WordSection1
{size:8.5in 11.0in;
margin:1.0in 1.0in 1.0in 1.0in;}
div.WordSection1
{page:WordSection1;}
--></style>
</head>
<body bgcolor="white" lang="EN-US" link="#0563C1" vlink="#954F72" style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;" class="">
<div class="WordSection1">
<p class="MsoNormal" style="text-autospace:none"><font face="Arial" style="font-size: 14px;" class="">The next Mobilize Center Seminar will be TODAY Thursday, November 17, and will feature Mobilize Center postdoctoral fellow, <b class="">Jason Fries</b>. We
look forward to seeing you!<o:p class=""></o:p></font></p>
<p class="MsoNormal" style="text-autospace:none"><font face="Arial" style="font-size: 14px;" class=""> <b class=""><o:p class=""></o:p></b></font></p>
<p class="MsoNormal" style="text-autospace:none"><font face="Arial" style="font-size: 14px;" class=""><b class="">TITLE:</b> <o:p class=""></o:p></font></p>
<p class="MsoNormal" style="text-autospace:none"><font face="Arial" style="font-size: 14px;" class=""><b class=""><u class="">Weak Supervision: Building Machine Learning Systems without Labeled Data</u></b><o:p class=""></o:p></font></p>
<p class="MsoNormal" style="text-autospace:none"><font face="Arial" style="font-size: 14px;" class=""> <o:p class=""></o:p></font></p>
<p class="MsoNormal" style="text-autospace:none"><font face="Arial" style="font-size: 14px;" class=""><b class="">WHEN:</b> <o:p class=""></o:p></font></p>
<p class="MsoNormal" style="text-autospace:none"><font face="Arial" style="font-size: 14px;" class=""><b class="">Thursday, November 17</b><o:p class=""></o:p></font></p>
<p class="MsoNormal" style="text-autospace:none"><font face="Arial" style="font-size: 14px;" class=""><b class="">noon - 1 pm</b> <o:p class=""></o:p></font></p>
<p class="MsoNormal" style="text-autospace:none"><font face="Arial" style="font-size: 14px;" class=""> <o:p class=""></o:p></font></p>
<p class="MsoNormal" style="text-autospace:none"><font face="Arial" style="font-size: 14px;" class=""><b class="">WHERE:</b> <o:p class=""></o:p></font></p>
<p class="MsoNormal" style="text-autospace:none"><font face="Arial" style="font-size: 14px;" class=""><b class=""><span style="color: rgb(251, 2, 7);" class="">Y2E2 300, Stanford University </span></b><o:p class=""></o:p></font></p>
<p class="MsoNormal" style="text-autospace:none"><font face="Arial" style="font-size: 14px;" class=""> <o:p class=""></o:p></font></p>
<p class="MsoNormal" style="text-autospace:none"><font face="Arial" style="font-size: 14px;" class=""><b class="">Abstract:</b><o:p class=""></o:p></font></p>
<div style="margin: 0in 0in 0.0001pt;" class=""><font face="Arial" style="font-size: 14px;" class=""><font class="">W</font>hile advances in deep learning are reducing the need for manual feature engineering in many machine learning tasks, current approaches
require large, labeled datasets to properly fit models. Unfortunately, in many domains training set creation itself is the primary bottleneck to building scalable machine learning systems. This motivates recent research on new ways to programmatically generate
labeled data, leveraging radically weaker and more diverse forms of supervision to train models at the scales required for automatic featurization. </font></div>
<div class=""><font face="Arial" style="font-size: 14px;" class=""><br class="">
</font></div>
<div class=""><font face="Arial" style="font-size: 14px;" class="">Data Programming is a newly proposed paradigm for training machine learning systems with unlabeled data. In this approach, users encode domain expertise and other forms of weak supervision as
labeling functions -- noisy, conflicting heuristics for labeling data. These functions train a generative model of the underlying labeling process, learning function accuracies to create a "denoised" instance of our training data for use in downstream discriminative
models. </font></div>
<div class=""><font face="Arial" style="font-size: 14px;" class=""><br class="">
</font></div>
<div class=""><font face="Arial" style="font-size: 14px;" class="">We present work on two learning systems developed using Snorkel, Stanford's open source data programming framework. First, we show a weakly-supervised named entity recognition system for tagging
disease and chemical names in PubMed abstracts. Evaluating our approach on three public biomedical datasets, we show that it is possible to approach traditional supervised performance without training on hand-labeled data, instead relying only on ontologies
and other domain heuristics.</font></div>
<div class=""><font face="Arial" style="font-size: 14px;" class=""><br class="">
</font></div>
<div class=""><font face="Arial" style="font-size: 14px;" class="">Second, we describe ongoing work analyzing text from the Stanford Hospital and Clinics electronic health record (EHR). Patient notes provide exciting analysis opportunities as they contain information
poorly captured elsewhere in the EHR. We examine a cohort of pre and post-operative joint replacement patients, using 1/2 million patient notes to extract relationships between anatomical locations and assessments of pain. We describe system performance and
future applications in medical device surveillance and other spontaneous reporting systems. </font></div>
<div class=""><font face="Arial" style="font-size: 14px;" class=""><br class="">
</font></div>
<div class=""><font face="Arial" style="font-size: 14px;" class="">The work is done in collaboration with Alison Callahan, Alex Ratner, Sen Wu, and Christopher Ré. </font></div>
<div class=""><font face="Arial" style="font-size: 14px;" class=""><br class="">
</font></div>
<p class="MsoNormal" style="text-autospace:none"><font face="Arial" style="font-size: 14px;" class=""><b class="">Bio:</b><o:p class=""></o:p></font></p>
<p class="MsoNormal" style="text-autospace:none"><span style="font-size: 14px;" class=""><font face="Arial" class="">Jason Fries is a Postdoctoral Fellow in Computer Science at Stanford University. He works with Prof. Chris Ré and Scott Delp as part of Stanford's
Mobilize Center, an NIH Big Data to Knowledge (BD2K) site of excellence that explores data science approaches to understanding diseases of human mobility. His research focuses on information extraction and predictive modeling using unstructured text and time
series data from scientific literature and the electronic medical record. His most recent projects include extracting named entities and relations from text without using labeled data and postoperative trajectories of pain and function after joint replacement
surgery. Jason received his PhD from the University of Iowa in 2015, co-advised by Alberto Segre and Dr. Phil Polgreen, working as part of Iowa's Computational Epidemiology Research Group. His thesis explored large-scale information extraction in electronic
medical record text as well as machine learning approaches to public health surveillance using social media. </font></span></p>
<p class="MsoNormal" style="text-autospace:none"><font face="Arial" style="font-size: 14px;" class=""> <o:p class=""></o:p></font></p>
<p class="MsoNormal" style="text-autospace:none"><font face="Arial" style="font-size: 14px;" class="">Please see<span style="color:#2B52FF" class=""> </span></font><a href="http://mobilize.stanford.edu/events/" class=""><span style="color:#6B006D" class="">Mobilize
Events</span></a><font face="Arial" style="font-size: 14px;" class=""> for a list of upcoming speakers.<o:p class=""></o:p></font></p>
<p class="MsoNormal" style="text-autospace:none"><font face="Arial" style="font-size: 14px;" class=""> <o:p class=""></o:p></font></p>
<p class="MsoNormal" style="text-autospace:none"><font face="Arial" style="font-size: 14px;" class="">Diane Bush<o:p class=""></o:p></font></p>
<p class="MsoNormal" style="text-autospace:none"><font face="Arial" style="font-size: 14px;" class="">Assistant to Professor Scott Delp<o:p class=""></o:p></font></p>
<p class="MsoNormal" style="text-autospace:none"><font face="Arial" style="font-size: 14px;" class="">NMBL, Mobilize Center, OpenSim<o:p class=""></o:p></font></p>
<p class="MsoNormal" style="text-autospace:none"><font face="Arial" style="font-size: 14px;" class="">Stanford University<o:p class=""></o:p></font></p>
<p class="MsoNormal"><font face="Arial" style="font-size: 14px;" class=""><a href="mailto:dbush1@stanford.edu" class=""><span style="color:#0000E9" class="">dbush1@stanford.edu</span></a><o:p class=""></o:p></font></p>
<p class="MsoNormal"><o:p class=""><font face="Arial" style="font-size: 14px;" class=""> </font></o:p></p>
<p class="MsoNormal"><o:p class=""><font face="Arial" style="font-size: 14px;" class=""> </font></o:p></p>
</div>
<br class="">
</body>
</html>