Skip to content

Details

I hope you have all been enjoying our recent online meetups, brought to in collaboration with the NY and Hungarian NLP groups. I'm pleased to announce a further online event, hosted by Seth Grimes of NY NLP. Further details as below, or feel free to refer to the meetup URL:

https://www.meetup.com/NY-NLP/events/271842037/

Moshe Wasserblat, NLP and Deep Learning Research Manager at Intel, will present on Simple and Efficient Deep Learning for Natural Language Processing. Our program starts at 1 pm US-Eastern (11 am US-Pacific, 6 pm BST, 7 pm CEST, 8 pm Israel).

Description: Large transformer-based neural networks such as BERT, GPT and XLNET have recently achieved state-of-the-art results in many NLP tasks. The success of these models is based on transfer learning between a generic task (for example, language modeling) and a specific downstream task.

However, the use of these generic pre-trained models come at a cost and challenges:

  1. The number of parameters and depth of the model brings a heavy computational burden, making then a non-energy efficient and challenge to deploy during inference.
  2. Deployment of these models in dynamic commercial environments often yield poor results. This is because commercial environments are usually dynamic, and contain continuous domain shifts (e.g. new themes, new vocabulary or new writing styles) between inference and training data.

In the first part of the session we will present the latest methods for efficient NLP like compression, quantization, and distillation with few real use-cases examples. In the second part of the session, we will focus on Aspect Based Sentiment Analysis application to demonstrate the challenges in low resource environments, and propose a step toward closing the gap with embedding structural information.

Speaker: Moshe Wasserblat is the NLP and DL Research Group manager for Intel’s AI-lab. Previously, he was with NICE Systems for more than 17 years, where he founded and led the speech and text analytics applied research team. He was the co-founder and coordinator of the EXCITEMENT FP7 ICT program and has filed more than 60 patents in the field of language technology.

By responding here, you acknowledge and consent to our Code of Conduct: We seek to provide a respectful, friendly, professional experience for everyone regardless of gender, sexual orientation, physical appearance, disability, age, race, and religion. We do not tolerate behavior that is harassing or degrading to any individual, in any form. Participants are responsible for knowing and abiding by these standards. We encourage all attendees to assist in creating a welcoming, safe, and respectful experience.

We are grateful for meetup support provided by Spark NLP publisher John Snow Labs (https://www.johnsnowlabs.com/).

You may also like