Microsoft Technology Licensing, LLC

Majid Yazdani

Craig Martell

Sanjay Kshetramade

Muhieddine El Kaissi

Alexander Chiocchi

Xiao Bao

Juan Pablo Bottaro

A method is provided. The method comprises receiving, from a user device, a current search query that is in an unstructured format; after receiving the current search query from the user device, retrieving a corresponding current list of facets with a current list of associated values and a context of the current search query, the context comprising a previous search query from the user device and a corresponding previous list of facets with a previous list of associated values; determining a group of actions on one or more of the current list of facets with the current list of associated values and the previous list of facets with the previous list of associated values based on the current search query; creating an updated list of facets with an updated list of associated values based on the group of actions; generating a database query based on the updated list of facets with the updated list of associated values; causing a database search with the database query; transmitting a search result of the database search to the user device, wherein the method is performed by one or more computing devices.

Facet-based conversational search

A method is provided. The method comprises receiving a search query that is part of a search conversation, the search query in an unstructured format; identifying a first list of facets with a first list of associated values from the search query; deriving a second list of facets with a second list of associated values from the first list of facets based on a context of the search query within the search conversation; generating a database query based on the second list of facets with the second list of associated values; causing a database search with the database query; transmitting a search result of the database search to a sender of the search query, wherein the method is performed by one or more computing devices.

In an example, for each of one or more terms in a text document, one or more entities to which the term potentially maps are identified. The text document includes at least one ambiguous term. One or more features are extracted from the text document. An attention model is applied to the text document based on the extracted one or more features, resulting in an attention weight being applied to each of the one or more terms in the text document. The one or more terms are encoded based on the attention weights. Each of one or more ambiguous terms is classified based on the encoded terms, the classification assigning a value to each different entity that each ambiguous term potentially maps to. A minimum entropy loss function is evaluated using the classification, and results are back-propagated to the attention model.

Growing community of inventors

Ranelagh, Ireland

Majid Yazdani