<div dir="ltr">Forwarding the following NLP talk information at TTIC on Friday morning at 11 am. The speaker, Zhewei Sun, will join TTIC as a research assistant professor in the fall. The talk will be in-person at TTIC 529 and also on <a href="https://uchicago.zoom.us/j/98297764499?pwd=ajNQSTZnMHRmMENkd1hjdjlNeW1xdz09">zoom</a>, and you can sign up to meet with the speaker <a href="https://docs.google.com/spreadsheets/d/1GLDLCBdsVbwSDeSyT6JctJq0JyrWclfFgkoHz69V4hI/edit?usp=sharing">here</a>!<div><br></div><div><br></div><div>Best,</div><div><br clear="all"><div><div dir="ltr" class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><div style="color:rgb(136,136,136);font-size:12.8px">Jiawei (Joe) Zhou</div><div style="color:rgb(136,136,136);font-size:12.8px"><span style="font-size:12.8px">TTIC</span><br></div><div style="color:rgb(136,136,136);font-size:12.8px"><span style="font-size:12.8px"><a href="mailto:jzhou@ttic.edu" target="_blank">jzhou@ttic.edu</a></span></div></div></div></div><br><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">---------- Forwarded message ---------<br>From: <strong class="gmail_sendername" dir="auto">Jiawei Zhou</strong> <span dir="auto"><<a href="mailto:jzhou@ttic.edu">jzhou@ttic.edu</a>></span><br>Date: Mon, Mar 18, 2024 at 12:04 PM<br>Subject: NLP Seminar 3/22 Friday 11:00 am - Zhewei Sun<br>To:  <<a href="mailto:nlp@lists.uchicago.edu">nlp@lists.uchicago.edu</a>><br></div><br><br><div dir="ltr"><span id="m_8834923102230272884gmail-docs-internal-guid-d88667ea-7fff-106d-1a2b-cffcce23f596"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Hi all,</span></p><br><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Welcome back from the spring break! We will resume our NLP seminar on Fridays 11:00 am - 12:00 pm at TTIC Room 529 (and on </span><a href="https://uchicago.zoom.us/j/98297764499?pwd=ajNQSTZnMHRmMENkd1hjdjlNeW1xdz09" style="text-decoration-line:none" target="_blank"><span style="font-size:11pt;font-family:Arial,sans-serif;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;text-decoration-line:underline;vertical-align:baseline">zoom</span></a><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">). For this week, we are excited to have Zhewei Sun from the University of Toronto visiting us in-person on 3/22. Zhewei will join TTIC this fall as a research assistant professor! If you want to meet him you can sign up </span><a href="https://docs.google.com/spreadsheets/d/1GLDLCBdsVbwSDeSyT6JctJq0JyrWclfFgkoHz69V4hI/edit?usp=sharing" style="text-decoration-line:none" target="_blank"><span style="font-size:11pt;font-family:Arial,sans-serif;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;text-decoration-line:underline;vertical-align:baseline">here</span></a><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">. Below is the talk information:</span></p><blockquote style="margin:0 0 0 40px;border:none;padding:0px"><span id="m_8834923102230272884gmail-docs-internal-guid-d88667ea-7fff-106d-1a2b-cffcce23f596"><br></span><span><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Title:</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Contextualizing Natural Language Agents: The Case of Slang</span></p></span><span><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline"> </span></p></span><span><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Abstract:</span></p></span><span><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Large language models (LLMs) have recently emerged as an effective tool for enhancing human productivity. Although conversational artificial intelligence (AI) agents such as ChatGPT produces natural language that is much more human-like compared to its predecessors, they still lack the ability to situate themselves in a communicative context like humans do. For instance, humans may opt to use informal language such as slang in a conversation to express a close bond with the other party. In this talk, I will illustrate how natural language processing (NLP) techniques can enable automatic processing of slang. The first part of my talk will cover knowledge-driven approaches that inject linguistic and cognitive knowledge about slang into foundational NLP models for (1) generation, (2) interpretation, and (3) modeling slang semantic variation. Next, I will discuss emerging data-driven approaches based on large language models, examining the extent of knowledge LLMs have acquired about slang and how such knowledge may have been obtained. Finally, I will discuss potential future directions to further enhance an LLM’s ability to process contextualized language.</span></p></span></blockquote></span><span><br></span><blockquote style="margin:0 0 0 40px;border:none;padding:0px"><span><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Bio:</span></p></span><span><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Zhewei Sun is a Ph.D. Candidate in the Department of Computer Science at the University of Toronto, working with Professor Yang Xu. His research is focused on natural language processing (NLP) of informal language, with a particular interest in the automatic processing of slang. His research explores both data-driven NLP approaches based on deep learning, as well as knowledge-driven approaches that combine traditional NLP techniques with linguistic and cognitive knowledge about human language. His work has been recognized at top-tier NLP venues, including EMNLP, NAACL, and TACL. Zhewei’s work has been supported in part by Amazon Alexa AI and the Queen Elizabeth II Graduate Scholarship in Science and Technology. Prior to joining the University of Toronto, Zhewei received an M.Sc. in Computer Science from Georgia Institute of Technology and a B.Sc. in Computer Science from the University of Waterloo.</span></p></span></blockquote><span><br><br><br><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Best,</span></p></span><br><div><div dir="ltr" class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><div style="color:rgb(136,136,136);font-size:12.8px">Jiawei (Joe) Zhou</div><div style="color:rgb(136,136,136);font-size:12.8px"><span style="font-size:12.8px">TTIC</span><br></div><div style="color:rgb(136,136,136);font-size:12.8px"><span style="font-size:12.8px"><a href="mailto:jzhou@ttic.edu" target="_blank">jzhou@ttic.edu</a></span></div></div></div></div></div>
</div></div></div>