A microservice running in a cloud computing environment is operable to perform a coordinate-based search responsive to a request from a requester such as a viewer that serves a web application in a browser on a user device. The request contains a set of coordinates of a user-defined area which highlights information of interest that the user wants to redact from a document displayed by the viewer on the user device. The document is a rendition of an internal representation generated from an original source document. The internal representation has a coordinate system that maps the location of text data in the original source document. The microservice utilizes the coordinate system to search every instance of the information of interest in the text data, generates corresponding bounding boxes, and sends the coordinates of the bounding boxes to the viewer which creates the bounding boxes to highlight/block all the instances.

A system for classifying a language sample intent by receiving a language sample including a set of features, identifying language sample features, determining a tokenization score for the language sample according to the language sample features, eliminating duplicate features according to the tokenization score, determining a term frequency (tf) according to the identified features and the tokenization score, determining an inverse document frequency (idf) according to the identified features and the tokenization score, and generating a term frequency-inverse document frequency (tf-idf) matrix for the identified features.

A computer-implemented method and system for enrichment of responses in a multimodal conversation environment are disclosed. A Question Answer (QA) engine, such as a reinforcement document transformer exploits a document template structure or layout, adapts the information extraction using a domain ontology, stores the enriched contents in a hierarchical form, and learns context and query patterns based on the intent and utterances of one or more queries. The region of enriched content for preparing a response to a given query is expanded or collapsed by navigating upwards or downwards in the hierarchy. The QA engine returns the most relevant answer with the proper context for one or more questions. The responses are provided to the user in one or more modalities.

A computer server system and method are disclosed for personalization and customization of network search results and rankings, such as for Internet searching. A representative server system comprises: a network interface to receive a query from a user and transmit return queries and search results; a data storage device having a first, lexical database having one or more compilations and templates; and one or more processors configured to access the first database and search a selected compilation using the query to generate initial search results; to comparatively score each selected parsed phrase of the initial search results, for each classification of a selected template and a selected compilation, and to output initial and final search results arranged according to the classifications and the predetermined order of the template. A representative embodiment may also include use of a second, semantic database having multi-dimensional vectors corresponding to parsed phrases, paragraphs, or clauses.

Generating a query response by receiving data for a non-user utterance, determining a question answering (QA) system response to the non-user utterance, receiving data for a user utterance responsive to the non-user utterance, determining a confidence score for the user utterance, determining a deviation between the user utterance and the QA system response, and providing the QA system response according to a combination of the deviation and the confidence score.

Methods, computer systems, computer-storage media, and graphical user interfaces are provided for facilitating data visualization generation. In one implementation, dataset intent data, visual design intent data, and insight intent data determined from a user input natural language query are obtained. A set of candidate intent recommendations is generated using various combinations of the dataset intent data, visual design intent data, and insight intent data. Each of the candidate intent recommendations is incorporated into a set of visualization templates to determine eligibility of the candidate intent recommendations. For eligible candidate intent recommendations, a score associated with a corresponding visualization template is determined. Based on the scores, a candidate intent recommendation and corresponding visualizations template is selected to use as a visual recommendation for presenting a data visualization.

A model training service of a provider network may receive content items as training data. For example, the content items may be documents with certain portions labeled as stale. The model training service may train one or more different types of models using those content items (e.g., natural language inference model, paraphrasing detection model, named entity recognition model). The model training service may then provide the model(s) to a content staleness check (CSC) service. The CSC service may receive, from a client, a request that indicates one or more content items to be checked for staleness. The CSC service may process the content items by the model(s) to generate one or more indications of staleness of the content item. The CSC service may generate a response based on the indications of staleness. For example, the CSC service may generate a document with certain portions highlighted as stale content.

In general, embodiments relate to a method for managing a technical support (TS) session on a technical support system. The embodiments include receiving TS correspondence from a client, wherein the TS correspondence is associated with the TS session, classifying the TS correspondence to assign it a question classification, based on the question classification, making a determination that the TS correspondence matches at least one prior received TS correspondence, wherein the at least one prior received TS correspondence is associated with the TS session, and visually identifying the TS correspondence and the at least one prior received TS correspondence on a graphical customer interface (GUI) of the technical support system.

A server, method, and non-transitory computer readable medium for ranking a plurality of data sources are provided. The server includes a network interface, a memory storage unit and a processor. The method involves receiving an input query, identifying entities of the input query using conditional random fields, generating a normalized query and applying a support vector machine to the normalized query. The non-transitory computer readable medium is encoded with programming instructions to direct a processor to carry out the method.

The present disclosure provides a method and apparatus for determining an extended reading content, a device, and a storage medium, relating to the field of data processing. The method may include: displaying a target page, in response to a viewing request to the target page; giving a reading prompt to an extended reading resource in the target page, based on a corresponding relationship between a requirement recognition result of at least one target reading content in the target page and the extended reading resource; and displaying the extended reading resource, in response to the viewing request matching the reading prompt.