<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body style="overflow-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;">
<div dir="auto" style="overflow-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;">
<i>Department of Computer Science Seminar</i></div>
<div dir="auto" style="overflow-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;">
<i><br>
</i></div>
<div dir="auto" style="overflow-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;">
<span><b>Saadia Gabriel </b></span></div>
<div dir="auto" style="overflow-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;">
<span><b>PhD Candidate</b></span></div>
<div dir="auto" style="overflow-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;">
<span><b>University of Washington</b></span></div>
<div dir="auto" style="overflow-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;">
<span><b><br>
</b></span></div>
<div dir="auto" style="overflow-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;">
<b>Tuesday, March 7th</b></div>
<div dir="auto" style="overflow-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;">
<b>2:00pm - 3:00pm </b></div>
<div dir="auto" style="overflow-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;">
<b style="background-color: rgb(245, 236, 0);">In Person: JCL 298</b></div>
<div dir="auto" style="overflow-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;">
<b><br>
</b></div>
<div dir="auto" style="overflow-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;">
<b>Zoom: </b></div>
<div dir="auto" style="overflow-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;">
<div dir="auto" style="overflow-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;">
<b><a href="https://uchicagogroup.zoom.us/j/99443964596?pwd=WjNuVm5MV3VtTldqck1qaTZKUk5ndz09">https://uchicagogroup.zoom.us/j/99443964596?pwd=WjNuVm5MV3VtTldqck1qaTZKUk5ndz09</a></b></div>
<div dir="auto" style="overflow-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;">
<br>
</div>
<div dir="auto" style="overflow-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;">
<b>Meeting ID: 994 4396 4596</b></div>
<div dir="auto" style="overflow-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;">
<b>Passcode: 261758</b></div>
<div dir="auto" style="overflow-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;">
<b><br>
</b></div>
</div>
<div dir="auto" style="overflow-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;">
<div><b>Title</b>: <b>Socially Responsible and Factual Reasoning for Equitable AI Systems</b></div>
<div><br>
</div>
<div><b>Abstract</b>:</div>
<div>Understanding the implications underlying a text is critical to assessing its impact. This requires endowing artificial intelligence (AI) systems with pragmatic reasoning, for example to infer that the statement “Epidemics and cases of disease in the 21st
century are “staged”” relates to unfounded conspiracy theories. In this talk, I discuss how shortcomings in the ability of current AI systems to reason about pragmatics leads to inequitable detection of false or harmful language. I demonstrate how these shortcomings
can be addressed by imposing human-interpretable structure on deep learning architectures using insights from linguistics.</div>
<div><br>
In the first part of the talk, I describe how adversarial text generation algorithms can be used to improve model robustness. I then introduce a pragmatic formalism for reasoning about harmful implications conveyed by social media text. I show how this pragmatic
approach can be combined with generative neural language models to uncover implications of news headlines. I also address the bottleneck to progress in text generation posed by gaps in evaluation of factuality. I conclude with an interdisciplinary study showing
how content moderation informed by pragmatics can be used to ensure safe interactions with conversational agents, and my future vision for development of context-aware systems.<br>
</div>
<div><br>
</div>
<div><b>Bio</b>: </div>
<div>Saadia Gabriel is a PhD candidate in the Paul G. Allen School of Computer Science & Engineering at the University of Washington, advised by Prof. Yejin Choi and Prof. Franziska Roesner. Her research revolves around natural language processing and machine
learning, with a particular focus on building systems for understanding how social commonsense manifests in text (i.e. how do people typically behave in social scenarios), as well as mitigating spread of false or harmful text (e.g. Covid-19 misinformation).
Her work has been covered by a wide range of media outlets like Forbes and TechCrunch. It has also received a 2019 ACL best short paper nomination, a 2019 IROS RoboCup best paper nomination and won a best paper award at the 2020 WeCNLP summit. Prior to her
PhD, Saadia received a BA summa cum laude from Mount Holyoke College in Computer Science and Mathematics.</div>
<div><br>
</div>
<div><img id="<0205FC0B-C17A-4460-88E0-BB6593C07D74>" src="cid:3CDFF15F-520E-4130-A7F7-E02924961B00" alt="74080742-C622-4860-BA7C-F1E4BDDD2FB0.jpeg" apple-inline="yes" class="Apple-web-attachment Singleton" style="opacity: 1;"></div>
</div>
<div>---</div>
<div>
<div>Holly Santos<br>
Executive Assistant to Michael J. Franklin, Chairman<br>
Department of Computer Science<br>
The University of Chicago<br>
5730 S Ellis Ave-217 Chicago, IL 60637<br>
P: 773-834-8977<br>
hsantos@uchicago.edu<br>
</div>
</div>
<br>
</body>
</html>