Suppose you had the same utterance but only “OS 9” was predicted by the learned component: In your utterance data, you have “I want to buy Proseware OS 9” with “Proseware OS 9” tagged as Software:īy using combine components, the entity will return with the full context as “Proseware OS 9” along with the key from the list component: Suppose you have an entity called Software that has a list component, which contains “Proseware OS” as an entry. When components are combined, you get all the extra information that’s tied to a list or prebuilt component when they are present. Use this to combine all components when they overlap. Combine componentsĬombine components as one entity when they overlap by taking the union of all the components. ![]() When an overlap occurs, each entity's final prediction is determined by one of the following options. When multiple components are defined for an entity, their predictions may overlap. While using the prediction API, you can specify the language in the input request, which will only match the regular expression associated to that language. In multilingual projects, you can specify a different expression for each language. A matched expression will return the key as part of the prediction response. You can have multiple regular expressions within the same entity, each with a different key identifier. When added, any text that matches the regular expression will be extracted. The regex component matches regular expressions to capture consistent patterns. See the list of supported prebuilt components for more information. You can have up to five prebuilt components per entity. When added, a prebuilt component is automatically detected. The prebuilt component allows you to select from a library of common types such as numbers, datetimes, and names. While using the prediction API, you can specify the language in the input request, which will only match the synonyms associated to that language. In multilingual projects, you can specify a different set of synonyms for each language. Each synonym belongs to a "list key", which can be used as the normalized, standard value for the synonym that will return in the output if the list component is matched. The component performs an exact text match against the list of values you provide as synonyms. The list component represents a fixed, closed set of related words along with their synonyms. If you do not tag any utterances with the entity, it will not have a learned component. This component is only defined if you add labels by tagging utterances for the entity. Your labels provide examples of where the entity is expected to be present in an utterance, based on the meaning of the words around it and as the words that were labeled. ![]() The model learns to predict where the entity is, based on the context within the utterance. The learned component uses the entity tags you label your utterances with to train a machine learned model. An entity can contain one component, which would determine the only method that would be used to extract the entity, or multiple components to expand the ways in which the entity is defined and extracted. Component typesĪn entity component determines a way you can extract the entity. You can determine the behavior of an entity prediction when its components overlap by using a fixed set of options in the Entity options. When an entity is defined by more than one component, their predictions can overlap. Every entity in your project is composed of one or more of these methods, which are defined as your entity's components. They can be learned through context, matched from a list, or detected by a prebuilt recognized entity. An entity can be extracted by different methods. In Conversational Language Understanding, entities are relevant pieces of information that are extracted from your utterances.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |