Abstract: A method includes receiving data characterizing a query for information associated with a first item of a plurality of items in an item catalog. The method also includes determining an attribute of the first item. The determining can be performed using a predictive model trained using question-answer pair data associated with a portion of the plurality of items. The portion can include a second item. The method can further include determining an attribute value of the attribute using a mapping of attributes and attribute values associated with the plurality of items in the item catalog. The method can also include providing, as an answer to the query, a characterization of the attribute value. Related systems, methods, apparatus, and computer readable mediums are also described.

Abstract: Data is received characterizing a plurality of search queries including user provided natural language representations of the plurality of search queries of an item catalogue and first labels associated with the plurality of search queries. Label weights characterizing a frequency of occurrence of the first labels within the received data is determined using the received data. Second labels are determined. The determining of the second labels includes removing or changing the first labels from the received data to reduce a total number of allowed labels for at least one search query. A classifier is trained using the plurality of search queries, the second labels, and the determined weights. The classifier is trained to predict, from an input search query, a prediction weight and at least one prediction label associated with the prediction weight. Related apparatus, systems, techniques, and articles are also described.

Abstract: A method includes receiving data characterizing a query for information associated with a first item of a plurality of items in an item catalog. The method also includes determining an attribute of the first item. The determining can be performed using a predictive model trained using question-answer pair data associated with a portion of the plurality of items. The portion can include a second item. The method can further include determining an attribute value of the attribute using a mapping of attributes and attribute values associated with the plurality of items in the item catalog. The method can also include providing, as an answer to the query, a characterization of the attribute value. Related systems, methods, apparatus, and computer readable mediums are also described.

Abstract: A method includes receiving data characterizing historical user interaction with a search engine associated with a plurality of items, the received data including a first search query and a first item name selected by a user in response to receiving a result of a search of the first search query; training, using the received data, a model that maps item names to referring expressions, the training including using the first item name selected by the user as an input to the model and the first search query as a supervisory signal to the model; and providing the model. Related apparatus, systems, techniques, and articles are also described.

Abstract: A method includes receiving data characterizing an utterance of a query associated with a tenant; providing, to an automated speech recognition engine, the received data and a profile selected from a plurality of profiles based on the tenant, the profile configuring the automated speech recognition engine to process the received data; receiving, from the automated speech recognition engine, a text string characterizing the query; and processing, via an ensemble of natural language agents configured based on the tenant, the text string characterizing the query to determine a textual response to the query, the textual response including at least one word from a first lexicon associated with the tenant. Related systems, methods, apparatus, and computer readable mediums are also described.

Abstract: A method includes receiving data characterizing an utterance of a query associated with a tenant; providing, to an automated speech recognition engine, the received data and a profile selected from a plurality of profiles based on the tenant, the profile configuring the automated speech recognition engine to process the received data; receiving, from the automated speech recognition engine, a text string characterizing the query; and processing, via an ensemble of natural language agents configured based on the tenant, the text string characterizing the query to determine a textual response to the query, the textual response including at least one word from a first lexicon associated with the tenant. Related systems, methods, apparatus, and computer readable mediums are also described.

Abstract: A method includes receiving data characterizing historical user interaction with a search engine associated with a plurality of items, the received data including a first search query and a first item name selected by a user in response to receiving a result of a search of the first search query; training, using the received data, a model that maps item names to referring expressions, the training including using the first item name selected by the user as an input to the model and the first search query as a supervisory signal to the model; and providing the model. Related apparatus, systems, techniques, and articles are also described.

Abstract: A method includes receiving data characterizing an utterance of a query associated with a tenant; providing, to an automated speech recognition engine, the received data and a profile selected from a plurality of profiles based on the tenant, the profile configuring the automated speech recognition engine to process the received data; receiving, from the automated speech recognition engine, a text string characterizing the query; and processing, via an ensemble of natural language agents configured based on the tenant, the text string characterizing the query to determine a textual response to the query, the textual response including at least one word from a first lexicon associated with the tenant. Related systems, methods, apparatus, and computer readable mediums are also described.

Abstract: A method includes receiving data characterizing historical user interaction with a search engine associated with a plurality of items, the received data including a first search query and a first item name selected by a user in response to receiving a result of a search of the first search query; training, using the received data, a model that maps item names to referring expressions, the training including using the first item name selected by the user as an input to the model and the first search query as a supervisory signal to the model; and providing the model. Related apparatus, systems, techniques, and articles are also described.