<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=us-ascii">
</head>
<body style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class="">
This is an announcement of Chao-Chun Hsu's MS Presentation<br class="">
===============================================<br class="">
Candidate: Chao-Chun Hsu<br class="">
<br class="">
Date: Wednesday, March 01, 2023<br class="">
<br class="">
Time: 3 pm CST<br class="">
<br class="">
Location: JCL 298
<div class=""><br class="">
</div>
<div class="">Remote Location: <a href="https://www.google.com/url?q=https://uchicago.zoom.us/j/94132202998?pwd%3DTFRpUXJrUW1KVW9udTJ2Zy81OVJ2UT09&sa=D&source=calendar&ust=1678026497926401&usg=AOvVaw1pxA7LKZ_mNapnGc7nK396" style="color: var(--primary); font-family: Roboto, Helvetica, Arial, sans-serif; font-variant-ligatures: normal; orphans: 2; widows: 2;" class=""><u class="">https://uchicago.zoom.us/j/94132202998?pwd=TFRpUXJrUW1KVW9udTJ2Zy81OVJ2UT09</u></a><span style="color: rgb(60, 64, 67); font-family: Roboto, Helvetica, Arial, sans-serif; font-variant-ligatures: normal; orphans: 2; widows: 2; text-decoration-thickness: initial;" class=""> (ID:
94132202998, passcode: H2965Wmi)</span><br class="">
<br class="">
M.S. Paper Title: On Predictability of Physician Notes<br class="">
<br class="">
Abstract: The success of large language models not only leads to substantial progress in NLP systems, but also provides exciting opportunities to characterize the predictability of human texts.<br class="">
In this work, we conduct the first large-scale systematic study of predictability in a wide range of text corpora, with an emphasis on physician notes.<br class="">
We show that physician notes are much more predictable than other texts.<br class="">
For example, the perplexity is only about 3 on physician notes, compared to 19 on Wikipedia and 12 on PubMed abstracts.<br class="">
We further examine the predictability of different physicians and patients, characterize what information is hard to predict, and investigate the flow of predictability in texts.<br class="">
Results show that notes for females and minorities groups have significantly lower perplexity compared to males and whites respectively.<br class="">
Perplexity flow analysis further reveals which sections in the physician note drive the differences between groups.<br class="">
Last but not least, we show that perplexity can serve as useful features for predicting clinical outcomes.<br class="">
<br class="">
Advisors: Chenhao Tan<br class="">
<br class="">
Committee Members: Chenhao Tan, Allyson Ettinger, and Ziad Obermeyer<br class="">
<br class="">
</div>
</body>
</html>