BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/Los_Angeles BEGIN:DAYLIGHT DTSTART:20180311T030000 TZOFFSETFROM:-0800 TZOFFSETTO:-0700 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:PDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20181104T010000 TZOFFSETFROM:-0700 TZOFFSETTO:-0800 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:PST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20180809T030842Z UID:D78C3FD9-AECE-4821-925E-26A70F1E4B54 DTSTART;TZID=America/Los_Angeles:20180731T183000 DTEND;TZID=America/Los_Angeles:20180731T203000 DESCRIPTION:Abstract:\n\nGenerative adversarial network (GAN) is a new idea for training models\, in which a generator and a discriminator compete ag ainst each other to improve the generation quality. Recently\, GAN has sho wn amazing results in image generation\, but the applications of GAN on te xt and speech processing are still limited. In this talk\, I will demonstr ate the applications of GAN on unsupervised abstractive summarization and sentiment controllable chat-bot. I will also talk about the research direc tions towards unsupervised speech recognition by GAN.\n\nBiography:\n\nHun g-yi Lee received the M.S. and Ph.D. degrees from National Taiwan Universi ty (NTU)\, Taipei\, Taiwan\, in 2010 and 2012\, respectively. From Septemb er 2012 to August 2013\, he was a postdoctoral fellow in Research Center f or Information Technology Innovation\, Academia Sinica. From September 201 3 to July 2014\, he was a visiting scientist at the Spoken Language System s Group of MIT Computer Science and Artificial Intelligence Laboratory (CS AIL). He is currently an assistant professor of the Department of Electric al Engineering of National Taiwan University\, with a joint appointment at the Department of Computer Science & Information Engineering of the unive rsity. His research focuses on machine learning (especially deep learning) \, spoken language understanding and speech recognition. He owns a YouTube channel teaching deep learning (in Mandarin) with more than 1.2M views an d 20k subscribers (https://www.youtube.com/channel/UC2ggjtuuWvxrHHHiaDH1dl Q/playlists).\n\nSpeaker(s): Professor Hung-yi Lee\, \n\n2485 Augustine Dr \, \, CA \, Santa Clara\, California\, United States\, 95054 LOCATION:2485 Augustine Dr\, \, CA \, Santa Clara\, California\, United Sta tes\, 95054 ORGANIZER:paveltc@gmail.com SEQUENCE:1 SUMMARY:Generative Adversarial Network and its Applications to Human Langua ge Processing URL;VALUE=URI:https://events.vtools.ieee.org/m/174481 X-ALT-DESC:Description: <br /><p><strong><em>Abstract:</em></strong></p>\n< p><em>Generative adversarial network (GAN) is a new idea for training mode ls\, in which a generator and a discriminator compete against each other t o improve the generation quality. Recently\, GAN has shown amazing results in image generation\, but the applications of GAN on text and speech proc essing are still limited. In this talk\, I will demonstrate the applicatio ns of GAN on unsupervised abstractive summarization and sentiment controll able chat-bot. I will also talk about the research directions towards unsu pervised speech recognition by GAN.</em></p>\n<p>&nbsp\;</p>\n<p><strong>< em>Biography:</em></strong></p>\n<p><em>Hung-yi Lee received the M.S. and Ph.D. degrees from National Taiwan University (NTU)\, Taipei\, Taiwan\, in 2010 and 2012\, respectively. From September 2012 to August 2013\, he was a postdoctoral fellow in Research Center for Information Technology Innov ation\, Academia Sinica. From September 2013 to July 2014\, he was a visit ing scientist at the Spoken Language Systems Group of MIT Computer Science and Artificial Intelligence Laboratory (CSAIL). He is currently an assist ant professor of the Department of Electrical Engineering of National Taiw an University\, with a joint appointment at the Department of Computer Sci ence &amp\; Information Engineering of the university. His research focuse s on machine learning (especially deep learning)\, spoken language underst anding and speech recognition.&nbsp\;He owns a YouTube channel teaching de ep learning (in Mandarin) with more than 1.2M views and 20k subscribers (< a href="https://www.youtube.com/channel/UC2ggjtuuWvxrHHHiaDH1dlQ/playlists ">https://www.youtube.com/channel/UC2ggjtuuWvxrHHHiaDH1dlQ/playlists</a>). </em></p> END:VEVENT END:VCALENDAR