<?xml version="1.0"?>
<News hasArchived="false" page="1" pageCount="1" pageSize="10" timestamp="Mon, 20 Apr 2026 15:47:20 -0400" url="https://dev.my.umbc.edu/groups/umbc-ai/posts.xml?tag=text">
  <NewsItem contentIssues="false" id="153614" important="false" status="posted" url="https://dev.my.umbc.edu/groups/umbc-ai/posts/153614">
  <Title>Talk: Inductive Analysis of Texts with Embeddings, 11/5</Title>
  <Tagline>12-1:30pm Wednesday, November 5, 2025, Commons 329</Tagline>
  <Body>
    <![CDATA[
    <div class="html-content"><h4>Inductive Analysis of Texts with Embeddings</h4><h4>Prof. <a href="https://my3.my.umbc.edu/groups/csss/events/145563/a6c/807b1717112ab90ff4d8fdacb5d94cce/web/link?link=https%3A%2F%2Fwww.dustinstoltz.com%2F" rel="nofollow external" class="bo">Dustin Stoltz</a>, Lehigh University</h4><p>Word or text <a href="https://en.wikipedia.org/wiki/Word_embedding" rel="nofollow external" class="bo"><strong>embeddings</strong></a> are a central component in modern language models, including those powering generative AI. Embeddings represent word meanings as positions in space, where words that are closer together are used in similar contexts or evoke similar concepts -- even if those words never actually co-occur. We navigate the meaning space created by embeddings directly using basic arithmetic, and in doing so, explore how meaning changes overtime or how meaning differs between different collections of texts. </p><p><a href="https://my3.my.umbc.edu/groups/csss/events/145563/a6c/807b1717112ab90ff4d8fdacb5d94cce/web/link?link=https%3A%2F%2Fwww.dustinstoltz.com%2F" rel="nofollow external" class="bo"><strong>Dustin Stoltz</strong></a> is an Assistant Professor of Sociology and Cognitive Science at Lehigh University.  He studies a variety of topics in cultural and economic sociology and specializes in computational methods.  Five copies of his recently published book, <a href="https://global.oup.com/academic/product/mapping-texts-9780197756881?cc=us&amp;lang=en&amp;" rel="nofollow external" class="bo">Mapping Texts: Computational Text Analysis for the Social Sciences</a> (coauthored with Marshall Taylor), will be raffled off to workshop registrants.  </p><h4><a href="https://my3.my.umbc.edu/groups/csss/events/145563" rel="nofollow external" class="bo">Register here.</a></h4><p>Lunch will be provided for registered attendees.</p><p>Hosted by the Center for Social Science Scholarship and cosponsored by the Departments of English; Sociology, Anthropology, &amp; Public Health; Modern Languages, Linguistics, &amp; Intercultural Communication; the Division of Information Technology; the Center for Scalable Data and Computational Science; and CGC-SCIPE.</p></div>
]]>
  </Body>
  <Summary>Inductive Analysis of Texts with Embeddings  Prof. Dustin Stoltz, Lehigh University  Word or text embeddings are a central component in modern language models, including those powering generative...</Summary>
  <Website>https://my3.my.umbc.edu/groups/csss/events/145563</Website>
  <TrackingUrl>https://dev.my.umbc.edu/api/v0/pixel/news/153614/guest@my.umbc.edu/26fc0b112f8765b28d76511cf407fd11/api/pixel</TrackingUrl>
  <Tag>ai</Tag>
  <Tag>analysis</Tag>
  <Tag>embeddings</Tag>
  <Tag>nlp</Tag>
  <Tag>text</Tag>
  <Group token="umbc-ai">UMBC AI</Group>
  <GroupUrl>https://dev.my.umbc.edu/groups/umbc-ai</GroupUrl>
  <AvatarUrl>https://assets4-dev.my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xsmall.png?1691095779</AvatarUrl>
  <AvatarUrl size="original">https://assets2-dev.my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/original.png?1691095779</AvatarUrl>
  <AvatarUrl size="xxlarge">https://assets1-dev.my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xxlarge.png?1691095779</AvatarUrl>
  <AvatarUrl size="xlarge">https://assets1-dev.my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xlarge.png?1691095779</AvatarUrl>
  <AvatarUrl size="large">https://assets1-dev.my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/large.png?1691095779</AvatarUrl>
  <AvatarUrl size="medium">https://assets3-dev.my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/medium.png?1691095779</AvatarUrl>
  <AvatarUrl size="small">https://assets3-dev.my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/small.png?1691095779</AvatarUrl>
  <AvatarUrl size="xsmall">https://assets4-dev.my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xsmall.png?1691095779</AvatarUrl>
  <AvatarUrl size="xxsmall">https://assets1-dev.my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xxsmall.png?1691095779</AvatarUrl>
  <Sponsor>UMBC AI</Sponsor>
  <ThumbnailUrl size="xxlarge">https://assets2-dev.my.umbc.edu/system/shared/thumbnails/news/000/153/614/9fbba467d186f849f1710ebc9e61c82f/xxlarge.jpg?1760577891</ThumbnailUrl>
  <ThumbnailUrl size="xlarge">https://assets3-dev.my.umbc.edu/system/shared/thumbnails/news/000/153/614/9fbba467d186f849f1710ebc9e61c82f/xlarge.jpg?1760577891</ThumbnailUrl>
  <ThumbnailUrl size="large">https://assets1-dev.my.umbc.edu/system/shared/thumbnails/news/000/153/614/9fbba467d186f849f1710ebc9e61c82f/large.jpg?1760577891</ThumbnailUrl>
  <ThumbnailUrl size="medium">https://assets3-dev.my.umbc.edu/system/shared/thumbnails/news/000/153/614/9fbba467d186f849f1710ebc9e61c82f/medium.jpg?1760577891</ThumbnailUrl>
  <ThumbnailUrl size="small">https://assets1-dev.my.umbc.edu/system/shared/thumbnails/news/000/153/614/9fbba467d186f849f1710ebc9e61c82f/small.jpg?1760577891</ThumbnailUrl>
  <ThumbnailUrl size="xsmall">https://assets3-dev.my.umbc.edu/system/shared/thumbnails/news/000/153/614/9fbba467d186f849f1710ebc9e61c82f/xsmall.jpg?1760577891</ThumbnailUrl>
  <ThumbnailUrl size="xxsmall">https://assets3-dev.my.umbc.edu/system/shared/thumbnails/news/000/153/614/9fbba467d186f849f1710ebc9e61c82f/xxsmall.jpg?1760577891</ThumbnailUrl>
  <ThumbnailAltText>Image of Dustin Stoltz, an Assistant Professor of Sociology and Cognitive Science at Lehigh University.</ThumbnailAltText>
  <PawCount>0</PawCount>
  <CommentCount>0</CommentCount>
  <CommentsAllowed>true</CommentsAllowed>
  <PostedAt>Thu, 16 Oct 2025 12:31:41 -0400</PostedAt>
  <EditAt>Sat, 18 Oct 2025 10:03:00 -0400</EditAt>
</NewsItem>
  <NewsItem contentIssues="false" id="144588" important="false" status="posted" url="https://dev.my.umbc.edu/groups/umbc-ai/posts/144588">
  <Title>Talk today on AI for Event-Centric Video Retrieval, 1:30pm in ITE 325b</Title>
  <Body>
    <![CDATA[
    <div class="html-content"><span><span>If you are interested in a challenging AI problem involving integrated spoken language and video understanding, Reno Kriz from JHU will discuss the results of a large summer project focused on finding videos about specific current events. His presentation will be at 1:30 p.m. today (Tuesday, 10/8) in ITE 325b and also online. Register and get more information </span><a href="https://my3.my.umbc.edu/groups/langtech/events/134555" rel="nofollow external" class="bo"><span>here</span></a><span>.</span></span></div>
]]>
  </Body>
  <Summary>If you are interested in a challenging AI problem involving integrated spoken language and video understanding, Reno Kriz from JHU will discuss the results of a large summer project focused on...</Summary>
  <Website>https://my3.my.umbc.edu/groups/langtech/events/134555</Website>
  <TrackingUrl>https://dev.my.umbc.edu/api/v0/pixel/news/144588/guest@my.umbc.edu/dfbc935fe3eaaed0ea7269f34ad72685/api/pixel</TrackingUrl>
  <Tag>ai</Tag>
  <Tag>audio</Tag>
  <Tag>nlp</Tag>
  <Tag>text</Tag>
  <Tag>video</Tag>
  <Tag>vision</Tag>
  <Group token="umbc-ai">UMBC AI</Group>
  <GroupUrl>https://dev.my.umbc.edu/groups/umbc-ai</GroupUrl>
  <AvatarUrl>https://assets4-dev.my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xsmall.png?1691095779</AvatarUrl>
  <AvatarUrl size="original">https://assets2-dev.my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/original.png?1691095779</AvatarUrl>
  <AvatarUrl size="xxlarge">https://assets1-dev.my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xxlarge.png?1691095779</AvatarUrl>
  <AvatarUrl size="xlarge">https://assets1-dev.my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xlarge.png?1691095779</AvatarUrl>
  <AvatarUrl size="large">https://assets1-dev.my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/large.png?1691095779</AvatarUrl>
  <AvatarUrl size="medium">https://assets3-dev.my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/medium.png?1691095779</AvatarUrl>
  <AvatarUrl size="small">https://assets3-dev.my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/small.png?1691095779</AvatarUrl>
  <AvatarUrl size="xsmall">https://assets4-dev.my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xsmall.png?1691095779</AvatarUrl>
  <AvatarUrl size="xxsmall">https://assets1-dev.my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xxsmall.png?1691095779</AvatarUrl>
  <Sponsor>Language Technology Seminar Series</Sponsor>
  <PawCount>0</PawCount>
  <CommentCount>0</CommentCount>
  <CommentsAllowed>true</CommentsAllowed>
  <PostedAt>Tue, 08 Oct 2024 10:10:00 -0400</PostedAt>
</NewsItem>
  <NewsItem contentIssues="true" id="141413" important="false" status="posted" url="https://dev.my.umbc.edu/groups/umbc-ai/posts/141413">
  <Title>Talk: Rigorous measurement in text-to-image systems, 4/29</Title>
  <Tagline>4-5pm ET Monday, April 29 in ENGR 231 and Webex</Tagline>
  <Body>
    <![CDATA[
    <div class="html-content"><div><h4><strong><br></strong></h4><h4><strong>Rigorous measurement in text-to-image systems (and AI more broadly?)</strong></h4><div><br></div><div><a href="https://saxon.me/" rel="nofollow external" class="bo"><strong>Michael Saxon</strong></a></div><div><strong>University of California, Santa Barbara</strong></div><div><strong><br></strong></div><div><strong>April 29, 2024 4:00 – 5:15 PM ET</strong></div><div><strong>ENGR 231 and <a href="https://umbc.webex.com/meet/gokhale" rel="nofollow external" class="bo">Webex</a></strong></div><div><br></div><div>As large pretrained models underlying generative AI systems have grown larger, inscrutable, and widely-deployed, interest in understanding their nature as emergent rather than engineered systems has grown. I believe to move this "ersatz natural science" of AI forward, we need to focus on building rigorous observational tools for these systems, which can characterize capabilities unambiguously. At their best, benchmarks and metrics could meet this need, but at present they are often treated as mere leaderboards to chase and only very indirectly measure capabilities of interest. This talk covers three works on this topic: first, a work laying out the high-level case for building a subfield of "model metrology" which focuses on building better benchmarks and metrics. Then, it covers two works on metrology in the generative image domain: first, a work which assesses multilingual conceptual knowledge in <a href="https://en.wikipedia.org/wiki/Text-to-image_model" rel="nofollow external" class="bo"><strong>text-to-image</strong></a> (T2I) systems, and second, a meta-benchmark that demonstrates how many T2I prompt faithfulness benchmarks actually fail to capture the compositionality characteristics of T2I systems which they purport to measure. This line of inquiry is intended to help move benchmarking toward the ideal of rigorous tools of scientific observation.</div><div><br></div><div><strong><a href="Michael%20Saxon" rel="nofollow external" class="bo">Michael Saxon</a></strong> is a PhD candidate and NSF Fellow in the NLP Group at the University of California, Santa Barbara. His research sits on the intersection of generative model benchmarking, multimodality, and AI ethics. He’s particularly interested in making meaningful evaluations of hard-to-measure new capabilities in these artifacts. Michael earned his BS in Electrical Engineering and MS in Computer Engineering at Arizona State University, advised by Visar Berish and Sethuraman Panchanathan in 2018 and 2020 respectively.</div></div><div><br><hr><a href="https://ai.umbc.edu/" rel="nofollow external" class="bo">UMBC Center for AI</a></div></div>
]]>
  </Body>
  <Summary>Rigorous measurement in text-to-image systems (and AI more broadly?)     Michael Saxon  University of California, Santa Barbara     April 29, 2024 4:00 – 5:15 PM ET  ENGR 231 and Webex     As...</Summary>
  <Website>https://www.tejasgokhale.com/seminar.html</Website>
  <TrackingUrl>https://dev.my.umbc.edu/api/v0/pixel/news/141413/guest@my.umbc.edu/a635851ae646611f8b11c1745ec96965/api/pixel</TrackingUrl>
  <Tag>ai</Tag>
  <Tag>image</Tag>
  <Tag>llm</Tag>
  <Tag>text</Tag>
  <Tag>text-to-image</Tag>
  <Group token="umbc-ai">UMBC AI</Group>
  <GroupUrl>https://dev.my.umbc.edu/groups/umbc-ai</GroupUrl>
  <AvatarUrl>https://assets4-dev.my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xsmall.png?1691095779</AvatarUrl>
  <AvatarUrl size="original">https://assets2-dev.my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/original.png?1691095779</AvatarUrl>
  <AvatarUrl size="xxlarge">https://assets1-dev.my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xxlarge.png?1691095779</AvatarUrl>
  <AvatarUrl size="xlarge">https://assets1-dev.my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xlarge.png?1691095779</AvatarUrl>
  <AvatarUrl size="large">https://assets1-dev.my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/large.png?1691095779</AvatarUrl>
  <AvatarUrl size="medium">https://assets3-dev.my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/medium.png?1691095779</AvatarUrl>
  <AvatarUrl size="small">https://assets3-dev.my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/small.png?1691095779</AvatarUrl>
  <AvatarUrl size="xsmall">https://assets4-dev.my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xsmall.png?1691095779</AvatarUrl>
  <AvatarUrl size="xxsmall">https://assets1-dev.my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xxsmall.png?1691095779</AvatarUrl>
  <Sponsor>UMBC AI</Sponsor>
  <ThumbnailUrl size="xxlarge">https://assets2-dev.my.umbc.edu/system/shared/thumbnails/news/000/141/413/3843538aec7e5167ea4f3e2c5a95c3eb/xxlarge.jpg?1714224563</ThumbnailUrl>
  <ThumbnailUrl size="xlarge">https://assets1-dev.my.umbc.edu/system/shared/thumbnails/news/000/141/413/3843538aec7e5167ea4f3e2c5a95c3eb/xlarge.jpg?1714224563</ThumbnailUrl>
  <ThumbnailUrl size="large">https://assets3-dev.my.umbc.edu/system/shared/thumbnails/news/000/141/413/3843538aec7e5167ea4f3e2c5a95c3eb/large.jpg?1714224563</ThumbnailUrl>
  <ThumbnailUrl size="medium">https://assets2-dev.my.umbc.edu/system/shared/thumbnails/news/000/141/413/3843538aec7e5167ea4f3e2c5a95c3eb/medium.jpg?1714224563</ThumbnailUrl>
  <ThumbnailUrl size="small">https://assets2-dev.my.umbc.edu/system/shared/thumbnails/news/000/141/413/3843538aec7e5167ea4f3e2c5a95c3eb/small.jpg?1714224563</ThumbnailUrl>
  <ThumbnailUrl size="xsmall">https://assets1-dev.my.umbc.edu/system/shared/thumbnails/news/000/141/413/3843538aec7e5167ea4f3e2c5a95c3eb/xsmall.jpg?1714224563</ThumbnailUrl>
  <ThumbnailUrl size="xxsmall">https://assets2-dev.my.umbc.edu/system/shared/thumbnails/news/000/141/413/3843538aec7e5167ea4f3e2c5a95c3eb/xxsmall.jpg?1714224563</ThumbnailUrl>
  <PawCount>0</PawCount>
  <CommentCount>0</CommentCount>
  <CommentsAllowed>true</CommentsAllowed>
  <PostedAt>Sat, 27 Apr 2024 09:34:44 -0400</PostedAt>
  <EditAt>Sat, 27 Apr 2024 10:07:37 -0400</EditAt>
</NewsItem>
</News>
