AutoText: An End-to-End AutoAI Framework for Text
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.
Cite
Text
Chaudhary et al. "AutoText: An End-to-End AutoAI Framework for Text." AAAI Conference on Artificial Intelligence, 2021. doi:10.1609/AAAI.V35I18.17993Markdown
[Chaudhary et al. "AutoText: An End-to-End AutoAI Framework for Text." AAAI Conference on Artificial Intelligence, 2021.](https://mlanthology.org/aaai/2021/chaudhary2021aaai-autotext/) doi:10.1609/AAAI.V35I18.17993BibTeX
@inproceedings{chaudhary2021aaai-autotext,
title = {{AutoText: An End-to-End AutoAI Framework for Text}},
author = {Chaudhary, Arunima and Issak, Alayt and Kate, Kiran and Katsis, Yannis and Valente, Abel N. and Wang, Dakuo and Evfimievski, Alexandre V. and Gurajada, Sairam and Kawas, Ban and Malossi, A. Cristiano I. and Popa, Lucian and Pedapati, Tejaswini and Samulowitz, Horst and Wistuba, Martin and Li, Yunyao},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2021},
pages = {16001-16003},
doi = {10.1609/AAAI.V35I18.17993},
url = {https://mlanthology.org/aaai/2021/chaudhary2021aaai-autotext/}
}