They're hints that LUIS can use, but they aren't hard rules. Machine-learning features give LUIS important cues for where to look for things that distinguish a concept. In machine learning, a feature is a distinguishing trait or attribute of data that your system observes and learns through. LUIS is meant to learn quickly with fewer examples. Don't add many patternsĭon't add too many patterns. There is no harm in adding them in the beginning of your model design, but it is easier to see how each pattern changes the model after the model is tested with utterances. You do not need to add them each time you iterate on the app's design. Once you understand how your app behaves, add patterns as they apply to your app. You should understand how the app behaves before adding patterns because patterns are weighted more heavily than example utterances and will skew confidence. Is is published in Frenchīest practices for Patterns: Do add patterns in later iterations. For example, the following template utterances: Using a Pattern.any entity in a pattern allows you to specify the beginning and end of the document name, so LUIS correctly extracts the form name. The utterances include words that may confuse LUIS about where the entity ends. Is Request relocation from employee new to the company 2018 version 5 is published in French?"."Who authored "Request relocation from employee new to the company 2018 version 5"?"." Where is Request relocation from employee new to the company 2018 version 5?".Utterances with the human-readable name might look like: However, each document has both a formatted name (used in the above list), and a human-readable name, such as Request relocation from employee new to the company 2018 version 5. This app might need to understand the following example utterances. The pattern.any entity allows you to find free-form data where the wording of the entity makes it difficult to determine the end of the entity from the rest of the utterance.įor example, consider a Human Resources app that helps employees find company documents. The pattern is applied at the token level, not the character level. Entities are required in the pattern for a pattern to match. Pattern matchingĪ pattern is matched by detecting the entities inside the pattern first, then validating the rest of the words and word order of the pattern. Patterns increase the confidence score without having to provide as many utterances. Given enough example utterances, LUIS can be able to increase prediction confidence without patterns. Prediction scores with and without patterns If two or more entities in a pattern are contextually related, patterns use entity roles to extract contextual information about entities. For simple entities to be utilized by your app, you need to add utterances or use list entities. While patterns use entities, a pattern does not help detect a machine-learning entity.ĭo not expect to see improved entity prediction if you collapse multiple utterances into a single pattern. The " pattern.any" entity is used to extract free-form entities. Patterns do not improve machine-learning entity detectionĪ pattern is primarily meant to help the prediction of intents and roles. Setting an intent for a template utterance in a pattern is not a guarantee of the intent prediction, but it is a strong signal. Patterns use a mix of prediction techniques.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |