YATO: Yet Another Deep Learning Based Text Analysis Open Toolkit

Abstract

We introduce YATO, an open-source, easy-to-use toolkit for text analysis with deep learning. Different from existing heavily engineered toolkits and platforms, YATO is lightweight and user-friendly for researchers from cross-disciplinary areas. Designed in a hierarchical structure, YATO supports free combinations of three types of widely used features including 1) traditional neural networks (CNN, RNN, etc.); 2) pre-trained language models (BERT, RoBERTa, ELECTRA, etc.); and 3) user-customized neural features via a simple configurable file. Benefiting from the advantages of flexibility and ease of use, YATO can facilitate fast reproduction and refinement of state-of-the-art NLP models, and promote the cross-disciplinary applications of NLP techniques. The code, examples, and documentation are publicly available at https://github.com/jiesutd/YATO. A demo video is also available at https://www.youtube.com/playlist?list=PLJ0mhzMcRuDUlTkzBfAftOqiJRxYTTjXH.

Contribution highlights

• We introduce YATO, an open-source, easy-to-use toolkit for text analysis with deep learning.

Extracted from the public abstract; no claims have been added.

Code and data

Publication metadata

DOI

10.18653/v1/2023.emnlp-demo.11

Version relationship

• Preprint: https://arxiv.org/abs/2209.13877
• Version of record: https://doi.org/10.18653/v1/2023.emnlp-demo.11

BibTeX

@inproceedings{Wang2023Yatoyet,
  title = {YATO: Yet Another Deep Learning Based Text Analysis Open Toolkit},
  author = {Zeqiang Wang and Yile Wang and Jiageng Wu and Zhiyang Teng and Jie Yang},
  booktitle = {Conference on Empirical Methods in Natural Language Processing (EMNLP), Demo},
  year = {2023},
  url = {https://arxiv.org/abs/2209.13877},
  doi = {10.18653/v1/2023.emnlp-demo.11}
}