BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Drupal//recurring_events_ical//2.0//EN
BEGIN:VEVENT
UID:a1ab5881-6fcd-4fec-974d-89e36729f216@support.access-ci.org
DTSTAMP:20240219T100631Z
DTSTART:20240222T160000Z
DTEND:20240222T210000Z
SUMMARY:Building Transformer Based Natural Language Processing Applications
  (NVIDIA Deep Learning Institute)
DESCRIPTION:Applications for natural language processing (NLP) and generati
 ve AI have exploded in the past decade. With the proliferation of applicat
 ions like chatbots and intelligent virtual assistants, organizations are i
 nfusing their businesses with more interactive human-machine experiences. 
 Understanding how transformer-based large language models (LLMs) can be us
 ed to manipulate, analyze, and generate text-based data is essential.Moder
 n pretrained LLMs can encapsulate the nuance, context, and sophistication 
 of language, just as humans do. When fine-tuned and deployed correctly, de
 velopers can use these LLMs to build powerful NLP applications that provid
 e natural and seamless human-computer interactions within chatbots, AI voi
 ce agents, and more. Transformer-based LLMs, such as Bidirectional Encode
 r Representations from Transformers (BERT), have revolutionized NLP by off
 ering accuracy comparable to human baselines on benchmarks like SQuAD for 
 question answering, entity recognition, intent recognition, sentiment anal
 ysis, and more.By participating in this workshop, you’ll:• How transfo
 rmers are used as the basic building blocks of modern LLMs for NLP applica
 tions• How self-supervision improves upon the transformer architecture i
 n BERT, Megatron, and other LLM variants for superior NLP results• How t
 o leverage pretrained, modern LLM models to solve multiple NLP tasks such 
 as text classification, named-entity recognition (NER), and question answe
 ring• Leverage pretrained, modern NLP models to solve multiple tasks suc
 h as text classification, NER, and question answering• Manage inference 
 challenges and deploy refined models for live applications
URL:https://support.access-ci.org/events/7357
END:VEVENT
END:VCALENDAR