Natural language processing

Parse text by using a natural language processing (NLP) engine with IBM Robotic Process Automation. It enables tasks like extracting text entities, spell checking, and answering questions.

Natural language processing (NLP) is a branch of artificial intelligence that is concerned to make computers understand text and spoken words in the same way human beings can. It can interpret texts from various sources, analyzing and classifying them to extract meaningful data and take decisions.

Some of tasks that it runs include speech recognition, part of speech tagging, word sense disambiguation, named entity recognition (NEM), co-reference resolution, sentiment analysis, and natural language generation.

IBM RPA offers Watson® NLP and Legacy NLP providers for your use. They provide a set of NLP models, which you can use by setting a default NLP provider in your IBM RPA Control Center tenant or during your bot's runtime. Apply it by using NLP commands to run tasks like entity extraction, spell checking, text classification, and text summarization.

Important: Currently, Watson NLP does not support chatbots, knowledge bases, and text classification models. See the Commands that support Watson NLP.

• Data extraction
  You can extract meaningful data from text by using extractor commands.

• Knowledge bases
  You can create knowledge bases in IBM RPA for your robots to answer questions by searching answers from a knowledge base. The knowledge base is a machine learning model that contains data that is structured in questions and answers.

• Text classification
  You can create text classification models in IBM RPA for document labeling.