AutoText: An End-to-End AutoAI Framework for Text

Authors

  • Arunima Chaudhary IBM Research AI
  • Alayt Issak IBM Research AI
  • Kiran Kate IBM Research AI
  • Yannis Katsis IBM Research AI
  • Abel Valente IBM Research AI
  • Dakuo Wang IBM Research AI
  • Alexandre Evfimievski IBM Research AI
  • Sairam Gurajada IBM Research AI
  • Ban Kawas IBM Research AI
  • Cristiano Malossi IBM Research AI
  • Lucian Popa IBM Research AI
  • Tejaswini Pedapati IBM Research AI
  • Horst Samulowitz IBM Research AI
  • Martin Wistuba IBM Research AI
  • Yunyao Li IBM Research AI

Keywords:

AutoAI, AutoML, CASH, Text Classification

Abstract

Building models for natural language processing (NLP) tasks remains a daunting task for many, requiring significant technical expertise, efforts, and resources. In this demonstration, we present AutoText, an end-to-end AutoAI framework for text, to lower the barrier of entry in building NLP models. AutoText combines state-of-the-art AutoAI optimization techniques and learning algorithms for NLP tasks into a single extensible framework. Through its simple, yet powerful UI, non-AI experts (e.g., domain experts) can quickly generate performant NLP models with support to both control (e.g., via specifying constraints) and understand learned models.

Downloads

Published

2021-05-18

How to Cite

Chaudhary, A., Issak, A., Kate, K., Katsis, Y., Valente, A., Wang, D., Evfimievski, A., Gurajada, S., Kawas, B., Malossi, C., Popa, L., Pedapati, T., Samulowitz, H., Wistuba, M., & Li, Y. (2021). AutoText: An End-to-End AutoAI Framework for Text. Proceedings of the AAAI Conference on Artificial Intelligence, 35(18), 16001-16003. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17993