Natural Language Processing Version 12 takes advantage of the recent advances in deep learning to bring state-of-the-art capabilities in natural language understanding. New reading comprehension functions can be used on text to answer questions or extract semantic contents. Additionally, a collection of pre-trained neural net models is available to be used as is or fine-tuned to a specific language task. Finally, the neural network framework has been updated with specific capabilities for text, making it one of the easiest tools to solve natural language problems. Answer natural language questions from text. » Identify more than 200 entity types in text. » Find occurrences of identification elements such as phone numbers. » Extract text written in a given language or about a given topic. » Transfer knowledge of a built-in model to a new task. » Create a custom multilingual text tokenizer. » Learn to generate text. » Create a custom autocompleter. » Use recurrent layers to train a neural network classifier. » Create custom recurrent layers via net operators. » Related Examples Answer General Knowledge Questions » Harvest Entities in Text » Find Locations in Text » Find Dates in Text » Represent Word Semantics in Context » Mine Clinical Concepts » Enhance Sentiment Analysis Using Transfer Learning » Build Neural Nets for Any Language » Fill in Missing Words » Autocomplete Programs » Generate Pokémon Names Using a Neural Net » Generate Bird Names Using a Markov Chain »