Abstract: To provide automated categorization of structured textual content individual nodes of textual content, from a document object model encapsulation of the structured textual content, have a multidimensional vector associated with them, where the values of the various dimensions of the multidimensional vector are based on the textual content in the corresponding node, the visual features applied or associated with the textual content of the corresponding node, and positional information of the textual content of the corresponding node. The multidimensional vectors are input to a neighbor-imbuing neural network. The enhanced multidimensional vectors output by the neighbor-imbuing neural network are then be provided to a categorization neural network. The resulting output can be in the form of multidimensional vectors whose dimensionality is proportional to categories into which the structured textual content is to be categorized. A weighted merge takes into account multiple nodes that are grouped together.

Abstract: A technique produces a graph data structure based on at least partially unstructured information dispersed over web documents. The technique involves applying a machine-trained model to a set of documents (or, more generally “document units”) to identify topics in the documents. The technique then generates count information by counting the occurrences of the single topics and co-occurrences of parings of topics in the documents. The technique generates conditional probability information based on the count information. An instance of conditional probability information describes a probability that a first topic will occur, given an appearance of a second topic, and a probability that the second topic will occur, given an appearance of the first topic. The technique then formulates the conditional probability information in a graph data structure. The technique also provides an application system that utilizes the graph data structure to provide any kind of computer-implemented service to a user.

Abstract: Technologies pertaining to electronic document understanding are described herein. A document is received, wherein the document includes a section of a type. An image of the document is generated, and a candidate region is identified in the image of the document, wherein the candidate region encompasses the section. A label is assigned to the candidate region based upon text of the section, wherein the label identifies the type of the section. An electronic document understanding task is performed based upon the label assigned to the candidate region.

Abstract: A technique is described herein for allocating tasks within a distributed system. The distributed system includes plural computing devices. Each computing device, in turn, provides a bucket manager and at least one application instance. The bucket managers allocate work to the computing devices in units of buckets, in a manner governed by a set of application-specific initialization parameters. The bucket managers also perform their assignment function in cooperation with a separate storage and notification (S&N) system. The S&N system stores data nodes in a hierarchical data structure that reflect the assignment-related state of the distributed system. The S&N system also notifies the bucket managers upon changes in the data nodes. According to one provision, the bucket managers include logic that reduces expensive context changes when computing devices join and leave the distributed system.

Abstract: Technologies pertaining to ranking webpages in response to receipt of a query are described. A search engine receives a query and identifies webpages that are germane to the query. The search engine ranks the identified webpages to form a ranked list, wherein a first webpage is positioned in the ranked list based upon a static score assigned to the first webpage. The static score is based upon a weight assigned to a hyperlink in a second webpage, wherein the hyperlink points to the first webpage, and further wherein the weight is based upon a value of a feature of the hyperlink, such as a location of the hyperlink on the second webpage when the second webpage is rendered. Further, the second webpage includes several hyperlinks that point to different webpages, wherein each of the several hyperlinks has a different weight assigned thereto.

Abstract: Context-based multi-granularity intent discovery, in relation to determining the intent of a user-problem associated with one of a plurality of products, includes identifying each of the plurality of products in a base intent level of a hierarchical intent data structure, creating a first granularity level below the base intent level, and creating a subsequent granularity level. The first granularity level includes groupings of the plurality of user-problems created according to a first common intent feature; the common intent feature is related to a respective one of the plurality of products. The subsequent granularity level includes sub-groupings of the user-problems of a respective grouping with each sub-grouping created according to a second common intent feature. The second common intent feature of each sub-grouping is determined without consideration of the first common intent feature.

Abstract: A technique is described herein for processing network-accessible documents in a scalable and resource-efficient manner. A model-generating process provided by the technique includes three-phases. A first phase generates a set of sample documents associated with a particular class of documents, a second phase applies labels to the sample documents to produce a set of labeled documents, and a third phase generates at least one data-extraction model based on the set of labeled documents. The data-extraction model includes data-extracting logic for extracting at least one specified data item from new documents that match the class of documents. In a data-extracting process, the technique identifies a data-extraction model that applies to the new document and then applies that model.

Abstract: Provided are techniques for encrypting a virtual disk of a virtual computing instance (VCI) while the VCI is online and still running using a mirror driver. In certain aspects a mirror driver is a filter running in an I/O stack used for accessing a virtual disk, such that the mirror driver receives I/Os destined to the virtual disk and mirrors those I/Os to the virtual disk and one or more additional virtual disks. The mirror driver begins copying data from an unencrypted source virtual disk to a destination virtual disk, and the data is encrypted as it is stored in the destination virtual disk, while the VCI is still online. During the copying, as new writes are issued to the unencrypted source virtual disk from the VCI, the mirror driver mirrors the writes to both the unencrypted source virtual disk and the destination virtual disk.

Abstract: Techniques are disclosed relating to tokenized account information with integrated authentication. In some embodiments, a shared secret key is used for tokenization and authentication. In some embodiments, a payment device stores an encrypted version of the secret key and decrypts the secret key based on a user-provided password. In some embodiments, the payment device uses the secret key and a moving factor to generate a limited-use password. In some embodiments, the payment device uses the limited-use password to modify a first identifier of an account of the user. In some embodiments, the authentication system retrieves a stored version of the secret key and a copy of the account number using a second identifier. In some embodiments, the authentication system generates the limited-use password based on the stored secret key and a moving factor, de-tokenizes the modified first identifier, and compares the result with the retrieved copy of the account number.

Abstract: Configurations herein comprise a multi-layer framework to extract document structural data. The framework extracts structural data from raw, unstructured, electronic documents, for example, .pdf documents. Structural data refers to the semantic elements, for example, paragraphs, lists, tables, titles etc. that may be visible in the displayed document but not described in electronic data.

Abstract: A technique is described herein that receives a set of markup-language documents (e.g., HTML documents). The technique produces a set of object-model representations (VDOMs) based on the set of markup-language documents. For a given markup-language document, the producing operation involves accessing and processing information that is linked to the markup-language document. Each object-model representation also includes visual layout information that specifies a visual appearance of a page that would be produced upon display of the markup-language document by a browser application. The technique then generates transformation logic based on the set of markup-language documents and their corresponding VDOMs. The transformation logic, when applied to a new markup-language document, converts the new markup-language document into a corresponding VDOM without retrieving at least some information identified by links (if any) in the new markup-language document.

Abstract: Aspects herein comprise a browser application (for example, an extension) that allows an end user to provide annotated web content to an extraction service. A client-side user can execute the application to select and annotate the data on a web page, and the annotation can indicate a location of and an identification of the kind of data that is in the web page. Then, based on the annotated web pages, one or more template(s)/rule(s) can be developed for the web page. The templates/rules can then be analyzed to extract automatically the structure data for the web page, which can be provided to the user. The template(s)/rule(s) can be uploaded to an extraction service, which collects and manages the template(s)/rule(s). Then, the extraction service can send extracted structure data to end users or other applications.

Abstract: A technique is described herein for allocating tasks within a distributed system. The distributed system includes plural computing devices. Each computing device, in turn, provides a bucket manager and at least one application instance. The bucket managers allocate work to the computing devices in units of buckets, in a manner governed by a set of application-specific initialization parameters. The bucket managers also perform their assignment function in cooperation with a separate storage and notification (S&N) system. The S&N system stores data nodes in a hierarchical data structure that reflect the assignment-related state of the distributed system. The S&N system also notifies the bucket managers upon changes in the data nodes. According to one provision, the bucket managers include logic that reduces expensive context changes when computing devices join and leave the distributed system.

Abstract: A system and method for automatically detecting and extracting entity data from a web page is provided. The method may include detecting a pattern for an entity based on a visual layout of the web page. A region of the webpage corresponding to the pattern may be identified as including the entity data, where the entity data is in a semi-structured form. Within the region, properties associated with the entity may be detected, annotations for the properties may be determined, and a category for the entity may be identified, where the properties, annotations, and category may be used to construct a schema for a structured form of the entity data. A template may be generated based on the schema and applied to the web page to extract the entity data in the structured form.

Abstract: A system for extracting a key phrase from a document includes a neural key phrase extraction model (“BLING-KPE”) having a first layer to extract a word sequence from the document, a second layer to represent each word in the word sequence by ELMo embedding, position embedding, and visual features, and a third layer to concatenate the ELMo embedding, the position embedding, and the visual features to produce hybrid word embeddings. A convolutional transformer models the hybrid word embeddings to n-gram embeddings, and a feedforward layer converts the n-gram embeddings into a probability distribution over a set of n-grams and calculates a key phrase score of each n-gram. The neural key phrase extraction model is trained on annotated data based on a labeled loss function to compute cross entropy loss of the key phrase score of each n-gram as compared with a label from the annotated dataset.

Abstract: A system for extracting key phrase candidates from a corpus of documents, including a processor, a memory, and a program executing on the processor. The system is configured to run a key phrase model to extract one or more key phrase candidates from each document in the corpus and convert each extracted key phrase candidate into a feature vector. The key phrase model also filters the feature vectors to remove duplicates using a classifier that was trained on a set of key phrase pairs with manual labels indicating whether two key phrases are duplicates of each other, to produce remaining key phrase candidates. The system uses the remaining key phrase candidates in a computer-implemented application.

Abstract: Context-based multi-granularity intent discovery, in relation to determining the intent of a user-problem associated with one of a plurality of products, includes identifying each of the plurality of products in a base intent level of a hierarchical intent data structure, creating a first granularity level below the base intent level, and creating a subsequent granularity level. The first granularity level includes groupings of the plurality of user-problems created according to a first common intent feature; the common intent feature is related to a respective one of the plurality of products. The subsequent granularity level includes sub-groupings of the user-problems of a respective grouping with each sub-grouping created according to a second common intent feature. The second common intent feature of each sub-grouping is determined without consideration of the first common intent feature.

Abstract: A method includes determining a match score indicative of similarities between (1) signal information associated with a current route being traveled by a user in connection with a transaction with a merchant and (2) signal information associated with an established route traveled by the user in connection with a previous transaction between the user and the merchant, wherein the signal information comprises signal signatures that identify one or more signal emitters identified along each route. The method also includes determining whether the current route matches the established route based on whether the match score is above a threshold. The method further includes if the match score is below the threshold, transmitting a message indicating that the user was not authenticated.

Abstract: Systems and methods are described for encrypting a swap file in a computer system. The swap file can be encrypted by a background process executing on the computer system. Processing of paging swapping operations occurs independently and separately of the background encryption of the swap file. Processing a page swapping operation can include decrypting or encrypting data to be swapped involved in the paging operation depending on the paging operation and whether or not the data to be swapped is encrypted or not.

Abstract: Systems and methods are described for encrypting the virtual disk in a virtual machine (VM). The virtual disk can be encrypted by a background process executing on the host machine that hosts the VM. Input/output operations (I/Os) to the virtual disk issued by a guest operating system (OS) executing on the VM can be intercepted on the hypervisor of the host machine and processed during the background encryption. Processing of the I/Os occurs independently and separately of background encryption of the virtual disk. Processing an I/O can include decrypting or encrypting data involved in the I/O depending on the location on the virtual disk targeted by the I/O.