BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:US/Pacific BEGIN:DAYLIGHT DTSTART:20230312T030000 TZOFFSETFROM:-0800 TZOFFSETTO:-0700 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:PDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20231105T010000 TZOFFSETFROM:-0700 TZOFFSETTO:-0800 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:PST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20230927T194609Z UID:0F19F3CA-E4C8-4297-94B1-A52E5F21D187 DTSTART;TZID=US/Pacific:20230920T183000 DTEND;TZID=US/Pacific:20230920T203000 DESCRIPTION:Event Details\n\nThe emergence of Large Language Models has led to many breakthroughs in processing text and producing new and innovative products. Generative text is one of many applications in the Natural Lang uage Understanding space. Text analysis\, vectorization\, and word-embeddi ngs provide another way to analyze text to help drive business decisions i n scientifically repeatable ways.\n\nThe vectorization approach can be use d to explore datasets like product reviews\, open ended survey questions a nd trouble tickets to understand the context of a large set of text data i n seconds. A language model is created for each dataset (a targeted langua ge model) which can then be used to explore a specific set of text data. D atasets might include a hundred thousand or million product reviews or an open-ended survey question answered by fifty thousand employees to underst and what is going on with customers or employees at a very deep level.\n\n Large language models and vectorization use different approaches to unders tand and interpret text. While large language models like GPT-3 transform massive amounts of text into a single neural network for generating text\, the vectorization or word embeddings approach can be used on small or lar ge datasets in a repeatable and consistent manner\, allowing for more reli able data analysis of a specific set of data.\n\nCome and learn about natu ral language analysis and ways to process text in new and innovative ways. \n\nAbout the Speaker Wood Harter\n\nWilliam Wood Harter is a Chapman Univ ersity Alumnus and Adjunct professor who has worked in Aerospace\, Securit y\, Gaming\, and now Artificial Intelligence and Natural Language Analysis . He currently works as a Solutions Architect for Luminoso\, an award-winn ing leader in tools for understanding language around product reviews\, op en-ended survey questions\, trouble tickets\, and help desk transcriptions .\n\nNOTE: This is an IN PERSON meeting. To receive a link to the event's recording\, complete the survey referenced in the header or footer.\n\nCo- sponsored by: OC ACM [Actual Host] and Knobbe Martens [Physical Host]\n\nA genda: \n6:30 PM Networking at physical meeting location\n7:00 PM Announce ments and Presentation with Q&A\n8:00 PM Follow-up quesitons for presenter and networking\n8:30 PM Meeting Adjourned\n\n2040 Main St \, Ste 14\, Irv ine\, California\, United States LOCATION:2040 Main St \, Ste 14\, Irvine\, California\, United States ORGANIZER:AWBrown@USC.edu SEQUENCE:16 SUMMARY:"Natural Language Analysis: How To Understand Tons Of Text In Minut es" IEEE OCCS & OC ACM Mtg URL;VALUE=URI:https://events.vtools.ieee.org/m/371655 X-ALT-DESC:Description: <br /><p><span style="text-decoration: underline\;" ><strong>Event</strong> <strong>Details</strong></span><strong> &nbsp\;</s trong></p>\n<p>The emergence of Large Language Models has led to many brea kthroughs in processing text and producing new and innovative products. Ge nerative text is one of many applications in the Natural Language Understa nding space. Text analysis\, vectorization\, and word-embeddings provide a nother way to analyze text to help drive business decisions in scientifica lly repeatable ways.</p>\n<p>The vectorization approach can be used to exp lore datasets like product reviews\, open ended survey questions and troub le tickets to understand the context of a large set of text data in second s. A language model is created for each dataset (a targeted language model ) which can then be used to explore a specific set of text data. Datasets might include a hundred thousand or million product reviews or an open-end ed survey question answered by fifty thousand employees to understand what is going on with customers or employees at a very deep level.</p>\n<p>Lar ge language models and vectorization use different approaches to understan d and interpret text. While large language models like GPT-3 transform mas sive amounts of text into a single neural network for generating text\, th e vectorization or word embeddings approach can be used on small or large datasets in a repeatable and consistent manner\, allowing for more reliabl e data analysis of a specific set of data.</p>\n<p>Come and learn about na tural language analysis and ways to process text in new and innovative way s.</p>\n<p><strong><span style="text-decoration: underline\;">About the Sp eaker</span> Wood Harter</strong></p>\n<p>William Wood Harter is a Chapman University Alumnus and Adjunct professor who has worked in Aerospace\, Se curity\, Gaming\, and now Artificial Intelligence and Natural Language Ana lysis. He currently works as a Solutions Architect for Luminoso\, an award -winning leader in tools for understanding language around product reviews \, open-ended survey questions\, trouble tickets\, and help desk transcrip tions.</p>\n<p><span style="text-decoration: underline\;"><strong>NOTE:</s trong></span>&nbsp\; This is an IN PERSON meeting.&nbsp\; To receive a lin k to the event's recording\, complete the survey referenced in the header or footer.</p><br /><br />Agenda: <br /><p><span class="aBn" tabindex="0" data-term="goog_557201553"><span class="aQJ">6:30 PM Networking at physica l meeting location<br /></span></span><span class="aBn" tabindex="0" data- term="goog_557201553"><span class="aQJ">7:00 PM</span></span> Announcement s and Presentation with Q&amp\;A<br />8:00 PM Follow-up quesitons for pres enter and networking<br />8:30 PM Meeting Adjourned</p> END:VEVENT END:VCALENDAR