{"id":18048,"date":"2018-06-06T07:41:35","date_gmt":"2018-06-06T07:41:35","guid":{"rendered":"https:\/\/developer.kore.ai\/v10-3\/?post_type=docs&p=14269"},"modified":"2023-04-24T14:43:12","modified_gmt":"2023-04-24T13:43:12","slug":"nlp-guide","status":"publish","type":"post","link":"https:\/\/developer.kore.ai\/v10-3\/docs\/bots\/chatbot-overview\/nlp-guide\/","title":{"rendered":"Natural Language Processing (NLP)"},"content":{"rendered":"
<\/div>\r\n\t
\r\n\t\t
\r\n\t\t\t

Prerequisites<\/span><\/span><\/h1>\n

Key NLP concepts such as utterance, intent, or dialog task are discussed in the <\/span>Virtual Assistants Overview<\/span><\/a>.<\/span><\/p>\n

Introduction<\/span><\/span><\/h1>\n

Conversational VAs are all about enabling a machine to have natural conversations with users. The key for a conversational VA to understand human interactions lies in its ability to identify the user’s intention (Intent Detection), extract useful information (Entity Extraction), and map them to relevant actions or tasks (Dialog Task execution). <\/span><\/p>\n

NLP is the science of deducing the intention and related information from natural conversations. The conversation flow in Kore.ai virtual assistants passes through various Natural Language Understanding (NLU) engines and conversation engines before the VA decides upon action and response.<\/span><\/p>\n

This article provides an overview of the NLP flow within a Kore.ai virtual assistant and shows how you, as a developer, can leverage its features to build an efficient and accurate VA.<\/span><\/p>\n

Kore.ai’s NLP Approach<\/span><\/span><\/h1>\n

The Kore.ai Experience Optimization (XO) Platform employs a multi-engine approach to natural language, which combines the following three models for optimal outcomes:<\/span><\/p>\n

    \n
  1. Fundamental Meaning (FM):<\/strong> A computational linguistics approach that is built on ChatScript. The model analyzes the structure of a user’s utterance to identify each word by meaning, position, conjugation, capitalization, plurality, and other factors;<\/span><\/li>\n
  2. Machine Learning (ML):<\/strong> Kore.ai uses state-of-the-art NLP algorithms and models for machine learning to enable VAs to be trained and to gradually improve their intelligence;<\/span><\/li>\n
  3. Knowledge Graph Engine (KG):<\/strong> The Knowledge Graph helps you turn your static FAQ text into an intelligent and personalized conversational experience.<\/span><\/li>\n<\/ol>\n

    With its three-fold approach, the Kore.ai XO Platform enables you to accelerate the Natural Language Understanding (NLU) performance of the virtual assistant and achieve optimal accuracy with relatively less training data. Kore.ai automatically enables the trained NLP capabilities to all built-in and custom VAs, and powers the way they communicate, understand, and respond to a user request.<\/span><\/p>\n

    NLP Building Blocks<\/span><\/span><\/h1>\n

    When a virtual assistant built on the Kore.ai XO Platform receives a user utterance, it is processed to identify the user intent, extract any additional information (entities), and then answer the user via a task execution. NLP is mostly concerned with the first two – intent detection and entity extraction.<\/span><\/p>\n

    \"\"<\/a><\/p>\n

    Steps in a Conversation Flow<\/span><\/span><\/h1>\n

    The Conversation Flow involves going through the following steps:<\/span><\/p>\n

      \n
    1. NLP Analysis<\/strong>: The user utterance goes through a series of NLP engines for entity extraction and intent detection. (You can extend the out-of-the-box NLP functionality to use your own engine. You can install the <\/span>Bot Kit SDK<\/span><\/a> and easily integrate the virtual assistant with any 3rd party NLP engine. The output from the 3rd party NLP engine complements the outputs from Kore.ai thus adding to the efficiency and accuracy of the engine.) The engines provided by the Kore.ai XO Platform are as follows:<\/span><\/li>\n