Use cases: NLP as used in actual projects

jeu. 17 janvier à 18:00

Ordina Mechelen
Malines
Belgique
Malines

--- Description ---

If you're attending in person, please leave a message in the comments with your preference for food (pizza, wraps, no preference) In this meetup Jan Bogaerts will share his expertise in the field of Natural Language Processing (NLP).

Katya and Pavel will share the awesome NLP work they are doing at Gini.

It's an updated version of their talk at this years ML Conference in Munich, so certainly worth your time! --- Agenda ---

• 18:00 - 18:30 - Free food & drinks, sponsored by Ordina

• 18:30 - 19:30 - introduction to NLP using SPACY

• 19:30 - 19:40 - Break

• 19:40 - 20:30 - From Prototype to Live Product: Understanding Documents with Deep Learning

• 20:30 - ??:?? - Drinks, discussions and fun --- Session 1 ---

  • introduction to NLP using SPACY * Text classification use case. Jan will talk about his project experience doing text classification and named entity recognition using spacy with hands on examples. Speaker: Jan Bogaerts

( https://www.linkedin.com/in/jan-bogaerts-8881a068 )

( http://www.elastetic.com )

Jan Bogaerts has co-created several startups in Belgium, including Bragisoft (creator of conversational agents) and AllThingsTalk (1st Belgian IoT platform). Currently, Jan is the founder of Elastetic, a small software development firm that specializes in IoT and Machine Learning solutions. --- Session 2 ---

  • From Prototype to Live Product: Understanding Documents with Deep Learning * Paying invoices can be quite a hassle. Visiting a bank, standing in a queue, manually filling forms takes a lot of time. Using online banking does not completely solve the problem either since you still need to type a lot. At Gini we have developed a solution called Photopay which enables users to pay their invoices just by taking a picture of it with your smartphone. In this talk we will walk you through how we have implemented Deep Learning (DL) technology into our information extraction system to extract information from document images. The talk will shed light onto the network architecture and how it is integrated into the information extraction pipeline. We will also share our experience of bringing DL prototypes developed in the research phase as POCs to actual live product, what difficulties we faced and how we solved them. Speakers: Katya Stalpouskaya & Pavel Shkadzko Katya has joined Gini GmbH as the Product Owner of Semantics in January 2017. Since then she has been driving the AI innovation within the company which has resulted in a dedicated research team working on DL solutions for information extraction. Before joining Gini Katya worked as a computational linguist on multiple NLP projects. She is also pursuing her PhD in Communication Science at Ludwig-Maximilian University of Munich. Pavel is a semantics engineer at Gini GmbH working on a neural based solution to improve the quality of information extraction from financial documents. He has conducted research in natural language generation and automatic semantic role labeling domain using neural and statistical approaches. Pavel acquired a master degree in Language Science and Technology from Saarland University (Saarbrucken) in 2018.

Source: https://www.meetup.com/fr-FR/Microsoft-Advanced-Analytics-User-Group/events/254246181/


Ordina Mechelen
Malines
Belgique

Technologie
Nous avons temporairement désactivé la possibilité de naviguer vers les tags.