{"id":17928,"date":"2016-10-28T17:08:25","date_gmt":"2016-10-28T17:08:25","guid":{"rendered":"https:\/\/developer.kore.com\/?post_type=docs&p=8558"},"modified":"2023-04-05T16:46:21","modified_gmt":"2023-04-05T15:46:21","slug":"user-utterances","status":"publish","type":"post","link":"https:\/\/developer.kore.ai\/v10\/docs\/bots\/nlp\/user-utterances\/","title":{"rendered":"The Machine Learning Engine"},"content":{"rendered":"
\r\n\t
\r\n\t\t
\r\n\t\t\t

Developers need to provide sample utterances for each intent (task) the assistant needs to identify, to train the machine learning model. The Kore.ai XO Platform Machine Learning (ML) engine will build a model that will try to map a user utterance to one of the VA’s intents.<\/span><\/p>\n

Kore.ai’s XO Platform allows fully unsupervised machine learning to constantly expand the language capabilities of your assistant – without human intervention. Unlike unsupervised models in which AI assistants learn from any input – good or bad – the Kore.ai XO Platform enables assistants to automatically increase their vocabulary only when the VA successfully recognizes the intent and extracts the entities of a human’s request to complete a task.<\/span><\/p>\n

However, we recommend keeping Supervised learning enabled to monitor the VA performance and manually tune where required. Using the XO Platform, developers can evaluate all interaction logs, easily change NL settings for failed scenarios, and use the learnings to retrain the VA for better conversations.<\/span><\/p>\n

This article discusses the processes behind the Machine Learning Engine, and how to perform training for optimum performance.<\/span><\/p>\n

The Machine Learning Process<\/span><\/span><\/h1>\n

Intent Detection<\/span><\/span><\/h2>\n

The below diagram summarizes the intent detection pipeline for both training and prediction stages. For the training pipeline, the language detection and auto-correction are not run with the assumption that the trainer would be aware of the language in which training needs to be done and of the spellings to be used which might include domain-specific non-dictionary words like Kore, etc.<\/span><\/p>\n

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

Entity Extraction<\/span><\/span><\/h2>\n

Entity extraction involves identifying any information provided by the user apart from the intent that can be used in the intent fulfillment. The entities are of three types<\/span><\/p>\n

    \n
  1. System entities<\/strong> like date, time, color, etc are provided out-of-the-box by the Platform. It includes nearly 22-24 entities and these are recognized by the ML engine automatically with no training except for string & description entity types.<\/span><\/li>\n
  2. Custom entities<\/strong> are defined by the bot developer and these include the list of values – enumerated, lookup, and remote, regex expressions, and composite entities. These are also mostly auto-detected by the ML engine.<\/span><\/li>\n
  3. NER or named entity recognition<\/strong> needs the training to identify the same entity type for different entities e.g. source & destination cities for flight booking intent, both of which are city type entities and the engine needs the training to distinguish between the two. NER can be conditional random field-based or neural network-based. CRF is preferred since it works on lesser data and has a faster training time compared to the NN-based method.<\/span><\/li>\n<\/ol>\n

    The following diagram summarizes the NER entity extraction pipeline.<\/span><\/p>\n

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

    ML Output<\/span><\/span><\/h2>\n

    The ML Engine runs the classification against the user utterance and generates the following scores output which Ranking and Resolver uses for identifying the correct intent:<\/span><\/p>\n