BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Asia/Kolkata BEGIN:STANDARD DTSTART:19451014T230000 TZOFFSETFROM:+0630 TZOFFSETTO:+0530 TZNAME:IST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20241004T133819Z UID:CE15C100-A2D1-4124-9E31-6CBE76E84782 DTSTART;TZID=Asia/Kolkata:20241003T170000 DTEND;TZID=Asia/Kolkata:20241003T180000 DESCRIPTION:Multimodal information processing deals with the efficient usag e of information available in different modalities such as audio\, video\, text\, etc. for solving various task applications of real life. This talk will discuss how the multimodal information extracted from different moda lities can help in improving different tasks of dialogue systems\, summari zation\, hate speech detection\, and complaint mining. Multimodal informat ion collected from audio tones\, facial expressions\, and texts is utilize d for determining the type of utterance in a multitask setting where emoti on recognition and dialogue act classification tasks are solved simultaneo usly. Multimodal information collected from videos\, images\, and texts ca n also be utilized for generating a summary. Images and texts collected fr om Amazon reviews are utilized for developing some aspect-based multimodal complaint detection systems in a multi-task setting where sentiment and e motion information are utilized as auxiliary tasks. Memes collected from s ocial media are utilized for the detection of hate speech in a multitask s etting where sentiment\, emotion\, and sarcasm detection are utilized as a uxiliary tasks. This talk will highlight these different applications of m ultimodal information processing in solving different NLP tasks.\n\nSpeake r(s): Sriparna Saha\, \n\nVirtual: https://events.vtools.ieee.org/m/436185 LOCATION:Virtual: https://events.vtools.ieee.org/m/436185 ORGANIZER:vinitkumargunjan@ieee.org SEQUENCE:15 SUMMARY:Multimodal Information Processing: Some recent NLP applications URL;VALUE=URI:https://events.vtools.ieee.org/m/436185 X-ALT-DESC:Description: <br /><p style="text-align: justify\;"><span style= "font-size: 12pt\; border: 1pt none windowtext\; padding: 0cm\;">Multimoda l&nbsp\;<wbr>information&nbsp\;processing&nbsp\;deals with the efficient u sage of&nbsp\;information&nbsp\;available in different modalities such as audio\, video\, text\, etc. for solving various task applications of real life. This talk will discuss how the&nbsp\;multimodal&nbsp\;information&nb sp\;<wbr>extracted from different modalities can help in improving differe nt tasks of dialogue systems\, summarization\, hate speech detection\, and complaint mining.&nbsp\;Multimodal&nbsp\;<wbr>information&nbsp\;collected from audio tones\, facial expressions\, and texts is utilized for determi ning the type of utterance in a multitask setting where emotion recognitio n and dialogue act classification tasks are solved simultaneously.&nbsp\;& nbsp\;Multimodal&nbsp\;<wbr>information&nbsp\;collected from videos\, imag es\, and texts can also be utilized for generating a summary. Images and t exts collected from Amazon reviews are utilized for developing some aspect -based&nbsp\;multimodal&nbsp\;<wbr>complaint detection systems in a multi- task setting where sentiment and emotion&nbsp\;information&nbsp\;are utili zed as auxiliary tasks. Memes collected from social media are utilized for the detection of hate speech in a multitask setting where sentiment\, emo tion\, and sarcasm detection are utilized as auxiliary tasks. This talk wi ll highlight these different applications of&nbsp\;multimodal&nbsp\;inform ation&nbsp\;<wbr>processing&nbsp\;in solving different NLP tasks.</span></ p> END:VEVENT END:VCALENDAR