FAQs

NLP++ is a generic NLP development framework that allows for building focused text analyzers that are 100% code, 100% modifiable, and 100% explainable. It was specially created for allowing users to encode linguistic, world, and algorithmic knowledge that mimics humans as they read and understand text when performing specific tasks. The resulting analyzers are robust and transparent that function well in real-world text processing tasks.

Other NLP systems provide generic processing with little or no modifications necessary but those systems are difficult or impossible to modify and almost never work for real-world tasks in NLP.

The idea that generic NLP parsers are useful for real-world NLP tasks is simply wrong. Real-world natural language understanding tasks are very specific and therefore cannot use generic NLP toolkits they are too difficult or impossible to modify for a specific task. NLP++ was created in order to create analyzers 100% customized to a specific task, providing a generic framework that allows for users to concentrate on creating the analyzer task without any extraneous programming.

Yes. There is a full English parser available. It is 100% modifiable code. There are also other analyzers that are available that are free to use as templates.

Yes. There is a growing number of free dictionaries, knowledge bases, and analyzers available to use in various languages. With time, using these resources will allow for faster and easier creation of text analyzers using NLP++.

The first step in customizing NLP++ is to determine how humans do a specific reading and understanding task. Once that is determined, dictionaries, knowledge bases, rules and function are created using the editor VisualText to mimic this task.

Yes, as of December 2018, VisualText and NLP++ source code is open source.

Yes! You can use this technology as much as you like for internal or personal use. As for December 2018, the code is now open source.

VisualText is an IDE made specifically to design, write, and debug text analyzers using NLP++ and Conceptual Grammar. It increases text analyzer building by up to 10 times.

NLP++ is a computer language to efficiently and intuitively write text analyzers.

The Conceptual Grammar is a hierarchical knowledge base that is used in VisualText analyzers and is used as a knowledge base for NLP++.

Yes, there is an beta version of an NLP Language Extension for VSCode found in our repository.

The limits of ML for NLP is due to the realty that linguistic knowledge and world-knowledge in our brains take anywhere from 4-14 years (depending on the language) to learn. Thinking that layers of neurons or statistical algorithms looking at millions of texts will solve this is not going to happen. If we build robots with brains, we still have to teach them language and everything about the world around them. It is a complex and changing thing that is intimately linked to our world model in our heads. The best way currently to write text analyzers that mimic what humans do is to think about a specific NLP task, find out what we need as humans to do it (the most efficient way), and then encode it. That is why NLP++ is so valuable in my opinion. It allows for the direct coding of human knowledge and processing to do each specific task, thus circumventing the need to create an “all-linguistic”, “all-knowing” program – something statistics and neural networks cannot mimic on their own.