We are a group of NLP enthusiasts who would like to offer a platform for learning and exchanging about Natural Language Processing andMachine Learning topics.
We organise a meetup every 6-8 weeks for NLP-interested people from both industry and academia in the Zurich Area. Our meetups include presentations/technical talks, knowledge sharing sessions (such as tutorials or workshops) and networking events.
We hope to grow and foster an active NLP community. Looking forward to meeting you!
If you would like to host us or give a talk please reach out to us! Looking forward to welcoming you.
Our topics of interest:
- Natural Language Processing - Machine Intelligence - Natural Language Understanding - Machine Learning - Text Analytics - Computational Linguistics - Text Mining - Automatic Text Understanding - Natural Language Generation - Cognitive Computing - Semantic Technology - Linked Data - Deep Learning - Language Technology
Please fill out the following form by 27th May for entrance badge registration. You will not be able to attend the event otherwise: https://www.zurich.ibm.com/meetup/nlp/
See you soon!
The 17th Natural Language Processing & Text Analytics Meetup will take place at IBM Research in Rüschlikon. We will hear about recent developments in word embeddings and how organic chemistry is just another NLP problem. Each presentation is 20−30 minutes followed by a short discussion time. Please RSVP on the meetup site. See you soon!
18:10–18:40 How computers solve language tasks: recent developments in word embeddings, self-attention and pre-training" by Ivan Girardi and Mario Zusag
18:40–19:10 "Found In Translation: Using Neural Translation Model to solve organic chemistry problem" by Philippe Schwaller
19:10–20:30 Networking Apero
Saeumerstrasse[masked] Rueschlikon, Switzerland
IBM Research (Thank you!)
"How computers solve language tasks: recent developments in word embeddings, self-attention and pre-training"
by Ivan Girardi and Mario Zusag
We will briefly describe recent improvements in language understanding, from Word2Vec via transformers to the guys from Sesame Street (BERT, ELMo). After that, we will present an application of those methods to Decision Support Systems. Given a specific patient presentation, the system is able to assess the level of medical urgency and issue the most appropriate recommendation in terms of best point of care and time to treat
"Found In Translation": Using Neural Translation Model to solve organic chemistry problem
by Philipp Schwaller
There is an intuitive analogy of an organic chemist's understanding of a compound and a language speaker's understanding of a word. Based on this analogy, it is possible to introduce the basic concepts and analyze potential impacts of linguistic analysis to the world of organic chemistry. In this work, we cast the reaction prediction task as a translation problem by using a Transformer model. Using an attention-based model borrowed from human language translation, we improve the state-of-the-art solutions in reaction prediction.