Phraser API is a semantic classifier for natural language questions, commands and intents. AI to power intelligent agents, Alexa skills and IoT devices. Deep Learning inside: no rules-based coding required. May I have email to send more information to?

Use Phraser API to power intelligent agents, Alexa skills, IoT devices, voice-enabled apps and chatbots. Convert natural language questions and commands to the canonical form a computer can understand. Deep Learning inside: no rules-based coding required. May I have email to send more information to?

Both FAQ API and Phraser API are based on our phrase2vec algorithm. Both take short natural language text as input. FAQ API is a question-answering system. It combines a search engine and intent classifier. It returns textual answers. ...

Our NLP engine doesn't rely on any ontologies, knowledge graphs or data representations. It's all pure statistical pattern recognition, powered by deep artificial neural network. It just learns from messy real world examples, like a child.

Use the Edit tab of the FAQ Editor to compose and/or edit your FAQ file. You may compose your FAQ right in the Edit tab or copy-paste from your existing FAQ file line-by-line. You can also upload the entire existing FAQ file. You may then edit it in the Edit tab. More here

You may include rich text (HTML) in your answers. In FAQ Editor, copy-paste it from an HTML or rich-text file. The bot will display the rich text in the web widget.

Users ask questions in their own words. Many of these questions are logically equivalent and shall be answered by the same answer. They are all paraphrases of one canonical question. These paraphrase questions are stored in the system and used for training AI. You may enter these paraphrase questions in the Edit tab. ...

Use the Label tab of FAQ Editor to label historical user queries. (Labeling means assigning the rights answers to these queries.) The system keeps a log of all user queries it receives. You may peruse and label these queries in the Label tab.  More here

Special classes: not all user queries shall be added to the training corpus. To process them, there is a number of pre-defined special classes: Wrong language, Garbage, Ignore and To do.  More here

The system keeps a log of all user queries it receives. They are displayed in the QUERY LOG column of the Label tab of FAQ Editor. You may peruse and label these queries there.  More here