{"id":18124,"date":"2019-02-12T09:36:25","date_gmt":"2019-02-12T09:36:25","guid":{"rendered":"\/docs\/bots\/bot-builder\/knowledge-graph\/"},"modified":"2021-03-25T09:16:10","modified_gmt":"2021-03-25T09:16:10","slug":"knowledge-graph","status":"publish","type":"post","link":"https:\/\/developer.kore.ai\/v7-0\/docs\/bots\/nlp\/knowledge-graph\/","title":{"rendered":"Knowledge Graph Training"},"content":{"rendered":"
\r\n\t
\r\n\t\t
\r\n\t\t\t

Training your Bot<\/a> is not restricted to Machine Learning and Fundamental Meaning engines. You need to train the Knowledge Graph engine, too.<\/p>\n

Knowledge Graph engine responds to users\u2019 intents by identifying the appropriate questions from the Knowledge Collection.<\/p>\n

Knowledge Graph<\/span><\/h3>\n

From the Knowledge Collection, follow these steps to build and train the corresponding Knowledge Graph:<\/p>\n

    \n
  1. Identify terms by grouping the unique words in each FAQ question. Build an ontology based on all such unique words.<\/li>\n
  2. Associate traits with terms to enable filtering FAQs from multiple identified results.<\/li>\n
  3. Define synonyms for each term\/node in the ontology. Ensure that all the different ways to call the term are defined.<\/li>\n
  4. Depending on the importance of each term in a path, mark them as either mandatory or regular.<\/li>\n
  5. Define alternative questions for each FAQ to ensure better coverage.<\/li>\n
  6. Manage Context for accurate response.<\/li>\n
  7. Stop Words can be used to filter unwanted utterances.<\/li>\n<\/ol>\n\r\n\t\t<\/div>\r\n\t<\/div>\r\n
    <\/div><\/div>\r\n\t
    \r\n\t\t
    \r\n\t\t\t

    Training and testing your Knowledge Collection is crucial to building a Knowledge Graph.<\/p>\n

    Before training, you can improve performance by using tags, synonyms, and traits.<\/p>\n

    Tags<\/h4>\n

    When you type a question in the User Says<\/b> field, the Knowledge Graph suggests some tags that you can add to the graph based on the text. To include a suggested term to the path, select the tag from the drop-down list that appears when the cursor is in the Add Term field. You can also add custom tags by typing them in the add term field and hitting the enter key.<\/p>\n

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

    Once you add a tag, it will be visible below the question like a tag everywhere the question appears. Tags work exactly like terms but are not displayed in the Bot Ontology to avoid clutter. You can add synonyms and traits to tags as you do to terms.<\/p>\n

    Synonyms<\/h4>\n

    You can add multiple synonyms for each term in your Knowledge Graph, making the path discoverable for varied user utterances. You can add synonyms for a term from the Settings window.<\/p>\n

    When you add a synonym for a term in the Knowledge Graph, you can add them as local (Path Level) or global (Knowledge Graph) synonyms.<\/p>\n

    Local synonyms<\/strong> apply to the term only in that particular path, whereas global synonyms<\/strong> apply to the term even if it appears on any other path in the ontology.<\/p>\n

    To add synonyms for a term<\/strong>:<\/p>\n

      \n
    1. On the top left side of your Bot Ontology, hover over the node\/term<\/strong> for which you want to add synonyms.<\/li>\n
    2. Click the gear icon<\/strong> to open the Settings window.<\/li>\n
    3. To add synonyms<\/strong>,\u00a0 do the following:\n