BEGIN:VCALENDAR VERSION:2.0 PRODID:-//128.220.36.25//NONSGML kigkonsult.se iCalcreator 2.26.9// CALSCALE:GREGORIAN METHOD:PUBLISH X-FROM-URL:https://www.clsp.jhu.edu X-WR-TIMEZONE:America/New_York BEGIN:VTIMEZONE TZID:America/New_York X-LIC-LOCATION:America/New_York BEGIN:STANDARD DTSTART:20231105T020000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RDATE:20241103T020000 TZNAME:EST END:STANDARD BEGIN:DAYLIGHT DTSTART:20240310T020000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RDATE:20250309T020000 TZNAME:EDT END:DAYLIGHT END:VTIMEZONE BEGIN:VEVENT UID:ai1ec-21259@www.clsp.jhu.edu DTSTAMP:20240328T154503Z CATEGORIES;LANGUAGE=en-US:Seminars CONTACT: DESCRIPTION:
Abstract
\nNatural language processin g has been revolutionized by neural networks\, which perform impressively well in applications such as machine translation and question answering. D espite their success\, neural networks still have some substantial shortco mings: Their internal workings are poorly understood\, and they are notori ously brittle\, failing on example types that are rare in their training d ata. In this talk\, I will use the unifying thread of hierarchical syntact ic structure to discuss approaches for addressing these shortcomings. Firs t\, I will argue for a new evaluation paradigm based on targeted\, hypothe sis-driven tests that better illuminate what models have learned\; using t his paradigm\, I will show that even state-of-the-art models sometimes fai l to recognize the hierarchical structure of language (e.g.\, to conclude that “The book on the table is blue” implies “The table is blue.”) Second\ , I will show how these behavioral failings can be explained through analy sis of models’ inductive biases and internal representations\, focusing on the puzzle of how neural networks represent discrete symbolic structure i n continuous vector space. I will close by showing how insights from these analyses can be used to make models more robust through approaches based on meta-learning\, structured architectures\, and data augmentation.
\nBiography
\nTom McCoy is a PhD candidate in the Department of Cognitive Science at Johns Hopkins University. As an undergr aduate\, he studied computational linguistics at Yale. His research combin es natural language processing\, cognitive science\, and machine learning to study how we can achieve robust generalization in models of language\, as this remains one of the main areas where current AI systems fall short. In particular\, he focuses on inductive biases and representations of lin guistic structure\, since these are two of the major components that deter mine how learners generalize to novel types of input.
DTSTART;TZID=America/New_York:20220131T120000 DTEND;TZID=America/New_York:20220131T131500 LOCATION:Ames Hall 234 @ 3400 N. Charles Street\, Baltimore\, MD 21218 SEQUENCE:0 SUMMARY:Tom McCoy (Johns Hopkins University) “Opening the Black Box of Deep Learning: Representations\, Inductive Biases\, and Robustness” URL:https://www.clsp.jhu.edu/events/tom-mccoy-johns-hopkins-university-open ing-the-black-box-of-deep-learning-representations-inductive-biases-and-ro bustness/ X-COST-TYPE:free X-TAGS;LANGUAGE=en-US:2022\,January\,McCoy END:VEVENT BEGIN:VEVENT UID:ai1ec-23894@www.clsp.jhu.edu DTSTAMP:20240328T154503Z CATEGORIES;LANGUAGE=en-US:Seminars CONTACT: DESCRIPTION:Abstract
\nThe use of NLP in the real m of financial technology is broad and complex\, with applications ranging from sentiment analysis and named entity recognition to question answerin g. Large Language Models (LLMs) have been shown to be effective on a varie ty of tasks\; however\, no LLM specialized for the financial domain has be en reported in the literature. In this work\, we present BloombergGPT\, a 50 billion parameter language model that is trained on a wide range of fin ancial data. We construct a 363 billion token dataset based on Bloomberg’s extensive data sources\, perhaps the largest domain-specific dataset yet\ , augmented with 345 billion tokens from general-purpose datasets. We val idate BloombergGPT on standard LLM benchmarks\, open financial benchmarks\ , and a suite of internal benchmarks that most accurately reflect our inte nded usage. Our mixed dataset training leads to a model that outperforms e xisting models on financial tasks by significant margins without sacrifici ng performance on general LLM benchmarks. Additionally\, we explain our mo deling choices\, training process\, and evaluation methodology.
\nBiography
Mark Dredze is the John C Malone Professo r of Computer Science at Johns Hopkins University and the Director of Rese arch (Foundations of AI) for the JHU AI-X Foundry. He develops Artificial Intelligence Systems based on natural language processing and explores app lications to public health and medicine.
\nProf. Dredze is affiliate d with the Malone Center for Engineering in Healthcare\, the Center for La nguage and Speech Processing\, among others. He holds a joint appointment in the Biomedical Informatics & Data Science Section (BIDS)\, under the Depart ment of Medicine (DOM)\, Division of General Internal Medicine (GIM) in th e School of Medicine. He obtained his PhD from the University of Pennsylva nia in 2009.
DTSTART;TZID=America/New_York:20230918T120000 DTEND;TZID=America/New_York:20230918T131500 LOCATION:Hackerman Hall B17 @ 3400 N. Charles Street\, Baltimore\, MD 21218 SEQUENCE:0 SUMMARY:Mark Dredze (Johns Hopkins University) “BloombergGPT: A Large Langu age Model for Finance” URL:https://www.clsp.jhu.edu/events/mark-dredze-johns-hopkins-university/ X-COST-TYPE:free X-TAGS;LANGUAGE=en-US:2023\,Dredze\,September END:VEVENT END:VCALENDAR