Computer-implemented systems and methods are provided for parsing search queries. In accordance with some embodiments, search records including character strings are retrieved, and search query templates are generated comprising sequences of categories corresponding to character substrings of the character strings. Also, in accordance with some embodiments, search queries are parsed into character substrings and matched with a search query template. The search query template may then be used to associate categories with the character substrings. A search engine may use the categories to focus or otherwise refine a search based on parsed search query.

Matching documents of a first kind (e.g., credit memos) to documents of a second kind (e.g., invoices) includes training a set of feature models and an all-features model. The set of feature models can be applied to unmatched documents of the first kind to produce predicted documents of the second kind. The predicted documents can be used to identify candidate documents as candidates to be matched to the unmatched documents.

Methods, systems, and apparatus, including computer programs encoded on a computer-readable storage medium and a method for automatically providing support solutions in response to user feedback items. The method comprises receiving user feedback items and corresponding support solutions. The method further comprises identifying, using clustering techniques, associations between the user feedback items and the corresponding support solutions. The method further comprises storing the identified associations as an items-solutions model that correlates the user feedback items with the corresponding support solutions. The method further comprises receiving a new user feedback item. The method further comprises automatically determining, using the items-solutions model, at least one support solution that corresponds to the new user feedback item. The method further comprises providing the at least one support solution in response to the received new user feedback item.

A category highly relevant to a keyword combination including a plurality of keywords is extracted. An information processing apparatus extracts a category where the number of times when the category is specified as a search condition along with a first keyword is greater than or equal to a first threshold value from among a plurality of categories that are hierarchized in a tree structure. Subsequently, from among categories corresponding to descendants of the extracted category, the information processing apparatus extracts a category where the number of times when the category is specified as a search condition along with a second keyword is greater than or equal to a second threshold value as a category relevant to a combination of the first keyword and the second keyword.

In one embodiment, the method includes a computing device receiving one or more characters as a user enters the characters into a graphical user interface (GUI) of the computing device. The method also includes the computing device determining one or more auto-suggestions, where each of the auto-suggestions presents a character string determined based at least in part on the entered characters. The method also includes the computing device determining a degree of difficulty of the user completing the respective character string for each of the auto-suggestions. The method further includes, for each of the auto-suggestions, if the degree of difficulty is at least approximately equal to or exceeds a pre-determined threshold, the computing device providing to the user the auto-suggestion for completing the character string.

In one embodiment, a method includes, by one or more computing systems, receiving, from a client system associated with a first user, a first user input from the first user, identifying one or more entities referenced by the first user input, determining a classification of the first user input based on a machine-learning classifier model, generating several candidate conversational fillers based on the classification of the first user input and the one or more identified entities, wherein each candidate conversational filler references at least one of the one or more identified entities, ranking the candidate conversational fillers based on a relevancy of the candidate conversational filler to the first user input and a decay model hysteresis, and sending instructions for presenting a top-ranked candidate conversational filler as an initial response to the first user.

An information processing apparatus includes a document information acquisition section that acquires document information with which a document type of a document is associated, a document type information acquisition section that acquires document type information, in which a reference range of a document referenced in a case of creating index data is set, for each document type of a document, and a creation section that creates the index data of the document with reference to a range of the document corresponding to the reference range set in the document type information associated with the document type of the document.

The present disclosure is directed toward systems and methods for utilizing semantic information in association with a search query. For example, one or more embodiments described herein identify key terms within a search query and utilize semantic information associated with the identified key terms to provide suggested replacement terms. A user can select one or more suggested replacement terms to broaden or refine a search query so as to add more meaning and specificity to the search query. Furthermore, one or more embodiments provide unique and interactive user interfaces to allow users to efficiently refine and improve search queries when using mobile devices with smaller or more limited display and input capabilities.

In one embodiment, a method includes receiving a sharing request to share content generated during a current dialog session from a client system associated with a first user, identifying one or more content objects associated with the sharing request based on a natural-language understanding module, wherein the one or more content objects were previously generated during the current dialog session, determining one or more second users the sharing request is directed to based on a user profile associated with first user, and sending instructions for accessing one or more of the identified content objects to one or more client systems associated with the one or more second users.

Technology of the disclosure may facilitate user discovery of various voice-based action queries that can be spoken to initiate computer-based actions, such as voice-based action queries that can be provided as spoken input to a computing device to initiate computer-based actions that are particularized to content being viewed or otherwise consumed by the user on the computing device. Some implementations are generally directed to determining, in view of content recently viewed by a user on a computing device, at least one suggested voice-based action query for presentation via the computing device. Some implementations are additionally or alternatively generally directed to receiving at least one suggested voice-based action query at a computing device and providing the suggested voice-based action query as a suggestion in response to input to initiate providing of a voice-based query via the computing device.