In today\u2019s post focusing on Azure Cognitive Analytics, I\u2019ll look at the Language Analytics APIs that are available. These language APIs allow your apps to process natural language with pre-built scripts, evaluate sentiment and learn how to recognize what users want. Often, you\u2019ll work with Speech and Language APIs together, but I\u2019ll cover Language today and Speech in my next post.<\/p>\n
Here\u2019s what is available in the Microsoft Language stack:<\/p>\n
1. Language Understanding Intelligence Service (LUIS)<\/strong> \u2013 The most commonly used in this stack; with it you can teach your apps to understand commands from your users. UPS uses this to help customers track their packages. It\u2019s also a great way to interact with Azure Bot Service where you can go in and ask questions in a bot and it will do the job of understanding what\u2019s been asked by understanding the language being used.<\/p>\n 2. Text Analytics API<\/strong> \u2013 This can easily evaluate sentiment and topics to understand what users want and use the language and context to decipher whether a person is happy or not, for instance. Let\u2019s say you use this with a customer survey and it will do some analytics to identify words like wonderful or terrible. It provides sentiment analysis for the organization, so you can move to another interaction level and respond, whether it\u2019s \u2018thanks for the great review\u2019 or \u2018sorry you had a bad experience, how can we help?\u2019<\/p>\n 3. Bing Spell Checker API<\/strong> \u2013 You can attach the Bing Spell Checker API to your application and it will detect and correct spelling mistakes.<\/p>\n 4. Translator Text API<\/strong> \u2013 This API will translate the text that typed in between languages, so you can work with third parties in other countries or provide customer service in a chat scenario when you\u2019re interacting with a person in another language. There are a lot of languages supported.<\/p>\n 5. Web Language Model API<\/strong> \u2013 Helps us handle natural language queries by using the power of predictive language models trained on web-scale data and understanding the next common word or providing word completion.<\/p>\n 6. Linguistic API<\/strong> \u2013 Currently in preview but brings in some very sophisticated linguistics technologies to simplify complex language concepts and parse text.<\/p>\n