John Doe has been working for the Microsoft company in Seattle since 1999.
Noun chunks is a core feature of Natural Language Processing. They are known as "noun phrases" in linguistics. Basicall they are nouns and all the words that depend on these nouns.
For example, let's say you have the following sentence:
John Doe has been working for the Microsoft company in Seattle since 1999.
Here are the noun chunks from this sentence:
Data scientists working on natural language processing are often interested in performing noun chunks extraction in their research activities. They also often need to automatically extract additional information like root text, root dependency, and root head text.
Noun chunks can also be used in real business situations, most of the time as a larger natural language processing pipeline. For example some companies use noun chunks to extract relevant keywords from articles as part of an SEO pipeline.
SpaCy is an excellent Natural Language Processing framework that performs fast and accurate noun chunk extraction in many languages (see more here). The Ginza model based on spaCy, released by Megagon Labs, is performing extremely well in Japanese (see the project here).
Building an inference API for noun chunk extraction is an interesting step that can definitely make Natural Language Processing easier to use for research or production use. Thanks to an API, you can automate your noun chunk extraction and do it in any programming language, not necessarily in Python.
NLP Cloud proposes a noun chunk API that gives you the opportunity to perform these operations out of the box, based on spaCy, and Ginza, with excellent performances. Noun chunk extraction is not very resource intensive, so the response time (latency), when performing them from the NLP Cloud API, is very good. You can do it in 15 different languages.
For more details, see our documentation about noun chunk extraction here.