HanLP 2.0.0-alpha.0 released. HanLP is composed of a series of models and algorithms Java toolkit aims to popularize the application of natural language processing in a production environment. HanLP with perfect features, performance efficiency, clear structure, when the corpus new, customizable features. At the same time provide a feature-rich, HanLP internal modules adhere to the low coupling, lazy loading model insist, insist on static service provided, expressly adhere to publish the dictionary, easy to use, and comes with a number of corpus processing tools to help users train their model.
HanLP 2.0 combines the properties have a large number of top-depth learning and natural language processing capabilities corpus unlabeled, updates include:
- Use TensorFlow 2.0 and Keras simple model construction and services.
- Multi-language support.
- Tokenized, speech tags, named entity recognition, syntactic and semantic dependency resolution, document classification through a unified interface.
Release Notes: