Last year Amazon announced a natural language processing tool, Comprehend, to help businesses extract common words and phrases from a corpus of information. On Monday, a week ahead of its Re: Invent customer conference, the company has announced an improvement to Comprehend that enables developers to build lists of specialized words and phrases without Machine Learning domain knowledge.
GM for Deep Learning and AI, Matt Wood said that they are delighted to bring new customization features to Comprehend that enable developers to extend Comprehend to classify natural language terms and classify text which is specialized to their team, business or industry. The key feature is that Amazon is handling all of the complexity, empowering developers to add customized lists without having Deep Machine Learning or natural language processing background. Wood said that Comprehend will do the heavy lifting to develop, train, and host the customized Machine Learning models, and make those models accessible through a private API.
Amazon is offering a way to build customized Machine Learning models while it takes care of the details behind the scenes. At their best, Cloud companies simplify the complex and provide access to sets of services that might be too difficult for many developers to accomplish on their own. Comprehend is trying to provide a way to create customized models without having any Machine Learning knowledge at all. The new Comprehend features are now generally available.