BEGIN:VCALENDAR VERSION:2.0 PRODID:-//events.la.psu.edu//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/New_York BEGIN:STANDARD DTSTART:20201101T020000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU END:STANDARD BEGIN:DAYLIGHT DTSTART:20200308T020000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU END:DAYLIGHT END:VTIMEZONE BEGIN:VEVENT UID:16884-5ab6e238307f066273d53169587c2098@events.la.psu.edu DTSTAMP:20260522T120326Z DTSTART;TZID=America/New_York:20220401T090000 DTEND;TZID=America/New_York:20220401T103000 SUMMARY:Lee Giles (Penn State) DESCRIPTION: How Deep Learning has Transformed Natural Language Processi ng orDid a Machine Really Say That?"\n\nFriday\, April 1\, 9:00–10:30 a. m. EDT\, via Zoom. \n\nDistinguished Language Science Colloquium\n\nDr. Lee Giles\n\nDavid Reese Professor at the School of Information Sciences and Technology at Penn State\n\nDeep learning (DL) is a rather new mach ine learning model strongly based on neural networks. It became popular primarily for performance reasons\, especially when it strongly outperfo rmed other machine learning methods\, first in the areas of computer vis ion\, then famously in natural language processing (NLP) such as machine translation\, all in this decade. Since then\, DL has continued to perf orm well on many large data problems and in related competitions and app lications seem to be proliferating. That being said\, there are many iss ues with Deep Learning. Here we will discuss its strengths and weaknesse s with some in NLP and offer suggested research directions. \n\nFor more details: https://events.la.psu.edu/event/lee-giles-penn-state/ X-ALT-DESC;FMTTYPE=text/html:

 How Deep Learning has Transfo rmed Natural Language Processing orDid a Machine Really Say That?"

Friday, April 1, 9:00–10:30 a.m. EDT, v ia Zoom. 

Distinguished Language Science Colloquium

Dr. Lee Giles

David Rees e Professor at the School of Information Sciences and Technology at Penn State< /p>

Deep learning (DL) is a rather new machine learning mo del strongly based on neural networks. It became popular primarily for p erformance reasons, especially when it strongly outperformed other machi ne learning methods, first in the areas of computer vision, then famousl y in natural language processing (NLP) such as machine translation, all in this decade. Since then, DL has continued to perform well on many lar ge data problems and in related competitions and applications seem to be proliferating. That being said, there are many issues with Deep Learnin g. Here we will discuss its strengths and weaknesses with some in NLP an d offer suggested research directions. 

For more details: https://events.la.psu.edu/event/lee-giles-pen n-state/

END:VEVENT END:VCALENDAR