Successful full-day BME TMIT & NVidia DLI workshop: Fundamentals of Natural Language Processing…

Source: Deep Learning on Medium

Successful full-day BME TMIT & NVidia DLI workshop: Fundamentals of Natural Language Processing with Deep Learning

BME TMIT and NVidia successfully held the 3rd NVidia DLI (Deep Learning Institute) workshop in Hungary on 1st October 2019. The topic of the workshop was Natural Language Processing (NLP) with Deep Learning. In this beginner & intermediate-level workshop, participants are introduced to word embeddings, text classification and neural machine translation.

The NVIDIA Deep Learning Institute (DLI) trains developers, data scientists, and researchers on how to use deep learning and accelerated computing to solve real-world problems across a wide range of domains. With access to GPU-accelerated workstations in the cloud, the participants learn how to train, optimize, and deploy neural networks using the latest deep learning tools, frameworks, and SDKs.

We started the workshop at 9:00 with an introduction of NLP for more than 60 participants.

Natural language processing (NLP) is a subfield of linguistics, computer science, information engineering, and artificial intelligence concerned with the interactions between computers and human (natural) languages, in particular how to program computers to process and analyze large amounts of natural language data. (Source: https://en.wikipedia.org/wiki/Natural_language_processing)

After the introduction, we had a short break and then continued with three major topics. We spent 2 hours with each topic: we started each 2 hours block with presenting the theory, which was followed by hands-on lab, done in the NVidia GPU cloud. The three topics were the following:

  1. Word embeddings with Word2Vec; training word embeddings with Keras.
  2. Character-based text classification on the Federalist Paper dataset with Long Short-Term Memory.
  3. Neural machine translation with sequence-to-sequence models, attention mechanism and application of NVidia Open Seq2seq.

The workshop could be done without any prior deep learning knowledge; however, some parts had advanced details, which was interesting and beneficial for experts too. Upon completing all the assessments of the hands-on labs, the attendees received an NVidia DLI Certificate. We finished the workshop at 17:00, however, the undone assessments can be completed at home by the participants, this way the certificate can be earned after the workshop as well.

The workshop was led by Dr. Bálint Gyires-Tóth (BME TMIT, NVidia DLI Certified Instructor and University Ambassador); Sevinj Yolchuyeva and Gergely Hajgató, deep learning PhD students, helped as teaching assistants.

Our host was EIT Digital, and the venue was the EIT Digital Co-Location Center Budapest. EIT Digital boosted the creativity of the participants with superb coffee and snacks, while the soft drinks and pizzas for lunch were sponsored by NVidia.

The next NVidia DLI workshop in Hungary will be in December 2019. Keep updated in the following Twitter channel: https://twitter.com/bapalto