BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Canada/Eastern BEGIN:DAYLIGHT DTSTART:20220313T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20221106T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20220428T230605Z UID:51C3055B-3106-4E37-A5DF-8DF152006368 DTSTART;TZID=Canada/Eastern:20220428T180000 DTEND;TZID=Canada/Eastern:20220428T190000 DESCRIPTION:Text Summarization is a technique for generating a concise and precise summary of voluminous texts while focusing on the sections that co nvey useful information without losing the overall meaning. It aims to tra nsform lengthy documents into shortened versions\, which could be difficul t and costly to undertake if done manually. With the current explosion of data circulating in digital space\, primarily unstructured textual data\, there is a need to develop tools that allow people to get insights from th em quickly. In situations where it is essential to keep track of what is b eing spoken\, such as during an online lecture\, taking notes is a popular activity used by many. The art of notetaking does not involve making note s of every single word that is spoken but comprehensive outlines of what i s discussed. The key to good notetaking lies in making concise yet informa tive summaries. In this seminar\, we will be discussing how we have tried to address the difficulties of notetaking by building an application that produces notes based on transcripts generated by the Automatic Speech Reco gnition (ASR) technology of the meeting platforms. We experimented with si x summarization models for this application\, including transformer-based models pre-trained on large corpora. The datasets used for this applicatio n are the transcripts dataset acquired from online meeting platforms and t he Extreme Summarization (XSum) dataset. We evaluated the models using Rou ge metrics (Rouge-1\, Rouge-2\, and Rouge-L) and selected the best-perform ing model as the final model. We have built a bot that utilizes Telegram ’s API and shares the generated summaries via group chat with the users. \n\nSpeaker(s): Manoj Varma Alluri\, \n\nToronto\, Ontario\, Canada\, Virt ual: https://events.vtools.ieee.org/m/312337 LOCATION:Toronto\, Ontario\, Canada\, Virtual: https://events.vtools.ieee.o rg/m/312337 ORGANIZER:reza.dibaj@ieee.org SEQUENCE:4 SUMMARY:Text Summarization of Transcripts from Online Meetings – Students Research in ML and DL at Durham College URL;VALUE=URI:https://events.vtools.ieee.org/m/312337 X-ALT-DESC:Description: <br /><p>Text Summarization is a technique for gene rating a concise and precise summary of voluminous texts while focusing on the sections that convey useful information without losing the overall me aning. It aims to transform lengthy documents into shortened versions\, wh ich could be difficult and costly to undertake if done manually. With the current explosion of data circulating in digital space\, primarily unstruc tured textual data\, there is a need to develop tools that allow people to get insights from them quickly. In situations where it is essential to ke ep track of what is being spoken\, such as during an online lecture\, taki ng notes is a popular activity used by many. The art of notetaking does no t involve making notes of every single word that is spoken but comprehensi ve outlines of what is discussed. The key to good notetaking lies in makin g concise yet informative summaries. In this seminar\, we will be discussi ng how we have tried to address the difficulties of notetaking by building an application that produces notes based on transcripts generated by the Automatic Speech Recognition (ASR) technology of the meeting platforms. We experimented with six summarization models for this application\, includi ng transformer-based models pre-trained on large corpora. The datasets use d for this application are the transcripts dataset acquired from online me eting platforms and the Extreme Summarization (XSum) dataset. We evaluated the models using Rouge metrics (Rouge-1\, Rouge-2\, and Rouge-L) and sele cted the best-performing model as the final model. We have built a bot tha t utilizes Telegram&rsquo\;s API and shares the generated summaries via gr oup chat with the users.</p> END:VEVENT END:VCALENDAR