{"674896":{"#nid":"674896","#data":{"type":"event","title":"PhD Defense by Jiaao Chen","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003ETitle:\u003C\/strong\u003E\u0026nbsp; Efficient and Adaptive Machine Learning for Natural Language Processing\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EDate:\u003C\/strong\u003E Tuesday, June 4, 2024\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ETime:\u003C\/strong\u003E 11:00am - 1:30pm EST\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ELocation (Zoom)\u003C\/strong\u003E:\u0026nbsp;\u003Ca href=\u0022https:\/\/gatech.zoom.us\/j\/93873694265?pwd=RUNaNWJLclhxMzBQM3BGNmJobVZrZz09\u0022 title=\u0022https:\/\/gatech.zoom.us\/j\/93873694265?pwd=RUNaNWJLclhxMzBQM3BGNmJobVZrZz09\u0022\u003Ehttps:\/\/gatech.zoom.us\/j\/93873694265?pwd=RUNaNWJLclhxMzBQM3BGNmJobVZrZz09\u003C\/a\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\u0022https:\/\/cs.stanford.edu\/people\/jiaaoc\/\u0022 title=\u0022https:\/\/cs.stanford.edu\/people\/jiaaoc\/\u0022\u003E\u003Cstrong\u003EJiaao Chen\u003C\/strong\u003E\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003EPhD Candidate\u003C\/p\u003E\u003Cp\u003ESchool of Interactive Computing\u003C\/p\u003E\u003Cp\u003ECollege of Computing\u003C\/p\u003E\u003Cp\u003EGeorgia Institute of Technology\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ECommittee\u003C\/strong\u003E:\u003C\/p\u003E\u003Cp\u003EDr. Diyi Yang (advisor), Computer Science Department, Stanford University\u003C\/p\u003E\u003Cp\u003EDr. Mark Riedl (co-advisor), School of Interactive Computing, Georgia Tech\u003C\/p\u003E\u003Cp\u003EDr. Alan Ritter, School of Interactive Computing, Georgia Tech\u003C\/p\u003E\u003Cp\u003EDr. Zsolt Kira, School of Interactive Computing, Georgia Tech\u003C\/p\u003E\u003Cp\u003EDr. Colin Raffel, Department of Computer Science, University of Toronto\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EAbstract:\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003ENLP has recently undergone a transformational shift towards the development and application of Large Language Models (LLMs), which represent a significant leap in performance. However, the extensive computational resources and the vast textual data sets on which they rely create key challenges in scenarios with limited resources, such as limited data, computational power, memory, and specialized expertise. I argue that developing machine learning methods that could efficiently adapt with limited resources is particularly vital in the era of LLMs to make the benefits of the technology sustainable, accessible, and generalizable.\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIn this thesis, I advocate for \u003Cstrong\u003Eefficient and adaptive machine learning for NLP\u003C\/strong\u003E, endeavoring to make NLP models benefit real-world applications by diving into three parts. Part I tackles the essential element of NLP learning, data. I propose to improve the data efficiency for developing NLP systems by\u0026nbsp;augmenting data through hidden space manipulation, linguistically informed perturbation, human learning strategies based generation and reasoning graphs. Part II deals with the information beyond the text in languages, structures. I explore what and how structures could be explicitly incorporated to enhance the NLP models. Part III focuses on the adapting process of NLP models, training. I investigate how we can efficiently fine-tune, update, and unlearn NLP models.\u003C\/p\u003E\u003Cp\u003E\u003Cbr\u003EFrom improving data efficiency and incorporating structures to improving training efficiency, this thesis aims to \u003Cstrong\u003Edevelop efficient and adaptive machine learning for NLP to democratize NLP systems with scarce resources, specialized fields, and emerging applications\u003C\/strong\u003E.\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EEfficient and Adaptive Machine Learning for Natural Language Processing\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Efficient and Adaptive Machine Learning for Natural Language Processing"}],"uid":"27707","created_gmt":"2024-05-24 19:34:53","changed_gmt":"2024-05-24 19:35:18","author":"Tatianna Richardson","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2024-06-04T11:00:00-04:00","event_time_end":"2024-06-04T13:00:00-04:00","event_time_end_last":"2024-06-04T13:00:00-04:00","gmt_time_start":"2024-06-04 15:00:00","gmt_time_end":"2024-06-04 17:00:00","gmt_time_end_last":"2024-06-04 17:00:00","rrule":null,"timezone":"America\/New_York"},"location":"Zoom","extras":[],"groups":[{"id":"221981","name":"Graduate Studies"}],"categories":[],"keywords":[{"id":"100811","name":"Phd Defense"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1788","name":"Other\/Miscellaneous"}],"invited_audience":[{"id":"78771","name":"Public"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}