Abstract: Contextual data corresponding to previous search requests of a service provider's electronic catalog can be used to resolve voice-input search requests and present search results. Contextual data includes the previous search request that is input to a machine learning algorithm along with a present search request. The machine learning algorithm generates a score indicative of whether the present search request is a refinement of the previous search or a new search request. Once the search request is classified as a refinement or a new search, the search is processed to provide search results including available items from the service provider matching the search request.

Abstract: Techniques are disclosed. The techniques include receiving, by a computing device, an answer to a query, the answer comprising a content element and a metadata element. Based on the content element and the metadata element, the techniques generate a presentable sentence of a plurality of presentable sentences. The techniques then utilize a machine learning model to determine a relevance score for the presentable sentence based on the query and the presentable sentence, the relevance score being of a set of relevance scores and corresponding to a measure of relevance with respect to the presentable sentence answering the query. The techniques then select a portion of the plurality of presentable sentences based on a ranking of the set of relevance scores and transmit the portion to a user device for presentation on a voice-based interface of the user device.

Abstract: A new model is introduced into a particular domain that receives a routing of a dialog from a speech processing component. The speech processing component is engaged in the dialog with a user and the speech processing component routes the dialog to the particular network-based domain according to a determination by the speech processing component that the user has an intent to perform a task handled by the domain. The model detects, at the domain, whether the user has the proper intent associated with the domain by using the user utterance in its entirety to yield a detection result. When the user does not have the proper intent based on the detection result, the domain drops the user utterance.