In this talk, I will discuss updates to Stanza, our Python natural language processing toolkit supporting 70 human languages. Compared to existing widely used toolkits, Stanza features a language-agnostic fully neural pipeline for text analysis, including tokenization, multi-word token expansion, lemmatization, part-of-speech and morphological feature tagging, dependency parsing, and named entity recognition.

I will talk about Stanza’s neural architectural design, its simple user interface, and its improved performance against existing toolkits over a range of datasets covering 70 languages. Our latest updates include NER support for a variety of new languages, a CNN-based sentiment model, a constituency parser, and a language detection model.

Lastly, I will talk about Stanza’s Python interface to the widely used Stanford CoreNLP Java library, which extends Stanza’s functionality to an even richer range of tasks.

I will close my talk by talking about our future plans for the Stanza library.