I need to buy those yellow sticky things for my home office Let’s say your assistant gets the following request: If you have experience with a live production assistant, you know that users find creative and unexpected ways to interact with your assistant. If Watson Assistant detects an entity but does not find an exact match for a synonym, it will only report the entity type However, if the recognized entity matches a synonym, Watson Assistant will report the normalized value too as note. You may want to normalize detected entities to a well-known value.Synonyms can provide hints to the machine learning algorithm to improve its entity recognition performance.There are two reasons why you may want to do this. You may wonder why we bothered to add synonyms to note entity value, since contextual entities do not perform exact dictionary matching. Let’s continue to annotate more examples, where the entity mentioned is not one of the values (i.e. But if you provide a sufficient number entity annotations, your assistant will eventually learn that “pen” in the context of this sentence is not an entity, hence the name “contextual entities”. Synonym and pattern matching would identify both “notepad” and “pen” as entities. I want to buy a notepad, so I can pen my new composition. For example, consider an utterance like this: The more annotated examples we provide, the better Watson Assistant will get at detecting contextual entities.Īlso, since Watson Assistant will be using the context, as opposed to an exact string or pattern match to recognize the entities, the precision of your assistant will increase. To make it work, we have to give more training examples to Watson Assistant by annotating more entities. This is because Watson Assistant needs to use the context of the annotated phrases to understand whether or not a given word is an instance of the entity or not. Just like humans, machine learning models need more than just one example to learn how your users will mention products they want to buy.Įven though entity has several values and synonyms, only the entities that are actually annotated are used as training data. In the example above, we only provided one training example to entity. However you need to provide a sufficient number of examples (as entity annotations on intents’ user examples) to properly train the entity detection algorithm. We can annotate the word “note pad” as utterance worked before we annotated an entity in a user example, so what happened to my entities?Īnnotating an entity is a signal to Watson Assistant to start using machine learning. Let’s look at the intent editing page where we can see user utterances for the #makePurchase intent. Instead of providing long lists of synonyms, you can annotate phrases in your intents’ user examples as entities. How can you accomplish this in Watson Assistant? The answer is contextual entities! That way, you can refer them to a partner, or maybe make a search in a product catalog to offer similar products you sell. Even though you do not offer these products yet, you may want your assistant to recognize these as an entity. You also notice that your users are asking for office products you are not selling yet. And failing to recognize these products, which are modeled as entity values, is causing your assistant to miss sales opportunities! As you start monitoring production logs to improve your assistant, you notice that your assistant’s users are referring to your products using phrases that are not expressed as synonyms in your entity model.
0 kommentar(er)
