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-20117@www.clsp.jhu.edu DTSTAMP:20240328T185129Z CATEGORIES;LANGUAGE=en-US:Seminars CONTACT: DESCRIPTION:
Abstract
\nNeural sequence generation systems oftentimes generate sequences by searching for the most likely se quence under the learnt probability distribution. This assumes that the mo st likely sequence\, i.e. the mode\, under such a model must also be the b est sequence it has to offer (often in a given context\, e.g. conditioned on a source sentence in translation). Recent findings in neural machine tr anslation (NMT) show that the true most likely sequence oftentimes is empt y under many state-of-the-art NMT models. This follows a large list of oth er pathologies and biases observed in NMT and other sequence generation mo dels: a length bias\, larger beams degrading performance\, exposure bias\, and many more. Many of these works blame the probabilistic formulation of NMT or maximum likelihood estimation. We provide a different view on this : it is mode-seeking search\, e.g. beam search\, that introduces many of t hese pathologies and biases\, and such a decision rule is not suitable for the type of distributions learnt by NMT systems. We show that NMT models spread probability mass over many translations\, and that the most likely translation oftentimes is a rare event. We further show that translation d istributions do capture important aspects of translation well in expectati on. Therefore\, we advocate for decision rules that take into account the entire probability distribution and not just its mode. We provide one exam ple of such a decision rule\, and show that this is a fruitful research di rection.
\nBiography
\nI am an assistant professor (UD) in natural language processing at the Institute for Logic\, Language and Computation where I lead the Probabilistic Language L earning group.
\nMy work concerns the design of models and algor ithms that learn to represent\, understand\, and generate language data. E xamples of specific problems I am interested in include language modelling \, machine translation\, syntactic parsing\, textual entailment\, text cla ssification\, and question answering.
\nI also develop techniques to approach general machine learning problems such as probabilistic inferenc e\, gradient and density estimation.
\nMy interests sit at the inter section of disciplines such as statistics\, machine learning\, approximate inference\, global optimization\, formal languages\, and computational li nguistics.
\n\n
DTSTART;TZID=America/New_York:20210419T120000 DTEND;TZID=America/New_York:20210419T131500 LOCATION:via Zoom SEQUENCE:0 SUMMARY:Wilker Aziz (University of Amsterdam) “The Inadequacy of the Mode in Neural Machine Translation” URL:https://www.clsp.jhu.edu/events/wilker-aziz-university-of-amsterdam/ X-COST-TYPE:free X-TAGS;LANGUAGE=en-US:2021\,April\,Aziz END:VEVENT BEGIN:VEVENT UID:ai1ec-23894@www.clsp.jhu.edu DTSTAMP:20240328T185129Z 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