YATO:又一个基于深度学习的文本分析开源工具包
YATO: Yet Another deep learning based Text analysis Open toolkit
AI总结:
本文介绍了轻量级、易用的深度学习文本分析开源工具包YATO,其采用分层结构支持传统神经网络、预训练语言模型及自定义特征自由组合,旨在促进最先进NLP模型的快速复现与跨学科应用。
摘要:
我们介绍了YATO,一个用于深度学习文本分析的开源、易用工具包。与现有过度工程化的工具包和平台不同,YATO轻量且对跨学科领域的研究人员用户友好。YATO采用分层结构设计,支持三种广泛使用的特征自由组合,包括:1)传统神经网络(CNN、RNN等);2)预训练语言模型(BERT、RoBERTa、ELECTRA等);3)通过简单的配置文件实现用户自定义的神经特征。得益于灵活性和易用性优势,YATO能够促进最先进NLP模型的快速复现与改进,并推动NLP技术的跨学科应用。代码、示例和文档已在 https://github.com/jiesutd/YATO 公开。演示视频也可在 https://www.youtube.com/playlist?list=PLJ0mhzMcRuDUlTkzBfAftOqiJRxYTTjXH 获取。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。