BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260703T212803Z
UID:77c7b417-c1bd-40ab-be60-70646bd97770
DTSTART:20220512T070000Z
DTEND:20220512T103000Z
DESCRIPTION:Overview\n\nNatural Language Processing is about techniques to 
 automatically extract relevant information from language\, primarily text.
  Recent advancements in NLP take the perspective of representation learnin
 g for language\, where language is represented by learned vectors in a hig
 h dimensional space. In this workshop we will look at how these learned r
 epresentations of language can be used to search for semantically similar 
 pieces of text. We will look at baselines techniques such as TF-IDF and co
 mpare it to contemporary methods using pre-trained Transformers.\n\nWe wil
 l work in Jupyter Notebooks with standard python libraries for contemporar
 y NLP such as GENSIM and Hugging Face Transformers. As an application we w
 ill look at patent data and how NLP can be used to create semantic represe
 ntation of patent applications for similarity search.\n\nPrerequisites\n\n
 You should be fluent in python and familiar with numpy. The workshop will 
 assume you have a basic grasp of linear algebra and probability theory.\n\
 nAgenda\n\nFor updated agenda please visit https://enccs.se/events/2022-0
 5-contemporary-nlp/\n\nFor questions regarding this event please contact u
 s at training@enccs.se.\n\n------------\n\nThis training is intended for 
 users established in the European Union or a country associated with Hori
 zon 2020. You can read more about the countries associated with Horizon20
 20 here https://ec.europa.eu/info/research-and-innovation/statistics/fram
 ework-programme-facts-and-figures/horizon-2020-country-profiles_en\n\n \n
 https://events.prace-ri.eu/event/1382/
SUMMARY:[ONLINE] Contemporary Natural Language Processing @ENCCS
URL;VALUE=URI:https://events.prace-ri.eu/event/1382/
END:VEVENT
END:VCALENDAR