Abstract
We introduce \texttt{N-LTP}, an open-source Python Chinese natural language processing toolkit supporting five basic tasks: Chinese word segmentation, part-of-speech tagging, named entity recognition, dependency parsing, and semantic dependency parsing. \texttt{N-LTP} adopts the multi-task framework with the pre-trained model to capture the shared knowledge across all Chinese relevant tasks. In addition, we propose to use knowledge distillation where single-task models teach a multi-task model, helping the multi-task model surpass its single-task teachers. Finally, we provide fundamental tasks API and a visualization tool to make users easier to use and view the processing results directly. To the best of our knowledge, this is the first toolkit to support all Chinese NLP fundamental tasks. Source code, documentation, and pre-trained models are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2009.11616
