ICLR 2019 Expo Talk


Expo 2019 Schedule »

NLP Architect by Intel AI Lab

Sponsor: Intel AI

Moshe Wasserblat (Speaker)


Deep-Learning, powerful computing resources and greater access to useful datasets drive many advances in Natural Language Processing (NLP) in recent years. At Intel AI Lab, our team of NLP researchers and developers released NLP Architect, an open source library, fully based on DL topologies, to share with the community and create a platform for future research and collaborations. In this session, we will review NLP Architect features and demonstrate how it makes easy for non-ML/NLP developers to build advanced NLP applications, for example, Un-supervised Aspect based Sentiment Analysis (ABSA), Set-Term Expansion, and Topic & Trend extraction. NLP Architect comes with a large number of models implementing SOTA algorithms and provided with end-to-end examples of training and inference processes. In addition, the library is modularized for easy integration and includes functionalities, such as data pipelines, dataset loader, common functional calls, and utilities related to NLP.