BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
X-WR-CALNAME:MS Thesis Final Exam - Raymond Baartmans
X-WR-TIMEZONE:Pacific Time (US & Canada)
BEGIN:VEVENT
DTSTAMP:20260612T083052Z
UID:tag:localist.com\,2008:EventInstance_52214832265959
DTSTART:20260306T180000Z
DTEND:20260306T190000Z
DESCRIPTION:TITLE: Towards Universal Semantics with Large Language Models\n
 \nABSTRACT: The Natural Semantic Metalanguage (NSM) is a linguistic theory
  based on a universal set of semantic primes: simple\, primitive word-mean
 ings that have been shown to exist in most\, if not all\, languages of the
  world. According to this framework\, any word\, regardless of complexity\
 , can be paraphrased using these primes\, revealing a clear and universall
 y translatable meaning. These paraphrases\, known as explications\, can of
 fer valuable applications for many natural language processing (NLP) tasks
 \, but producing them has traditionally been a slow\, manual process. In t
 his work\, we present the first study of using large language models (LLMs
 ) to generate NSM explications. We introduce automatic evaluation methods\
 , a tailored dataset for training and evaluation\, and fine-tuned models f
 or this task. Our 1B and 8B models outperform GPT-4o in producing accurate
 \, cross-translatable explications\, marking a significant step toward uni
 versal semantic representation with LLMs and opening up new possibilities 
 for applications in semantic analysis\, translation\, and beyond.\n\n \n\n
 MAJOR ADVISOR: Lizhong Chen\nCO-MAJOR ADVISOR: Huazheng Wang\nCOMMITTEE: S
 anghyun Hong\nCOMMITTEE: Stefan Lee\nGCR: Todd Stephen Palmer
LOCATION:
SUMMARY:MS Thesis Final Exam - Raymond Baartmans
URL;VALUE=URI:https://events.oregonstate.edu/event/ms-thesis-final-exam-ray
 mond-baartmans
CATEGORIES:Lecture or Presentation
END:VEVENT
END:VCALENDAR