Abstract: A computer-implemented method is provided. The method comprises: receiving, from a text field of a user interface, input text strings containing medical data; identifying, based on language semantics and grammatical structure, a keyword and one or more data values from the input text strings; providing the keyword as an input to a query of a medical data category database to obtain one or more categories associated with the keyword, the one or more categories including a first category; retrieving, from a template database, a first template associated with the first category, the first template including one or more fixed blocks and one or more variable blocks; inserting a data value corresponding to the keyword into a variable block of the first template to generate a replacement text string; and displaying the replacement text string in place of the input text strings in the text field.

Abstract: Systems and methods for linking a data set to respective locations of relevant data elements in documents included in electronic files in which a formatting server identifies a specific location of each occurrence of each of a plurality of different categories of fields in documents in an electronic file and links an identifier of each of the categories to each specific location of each of the occurrences. Thereafter, a review server compares data populating all of the occurrences at each specific location of at least one of the categories of fields to which the identifier of the particular category of fields is linked and generates a notification when the data populating any of the occurrences differs from data populating any of the other occurrences of the same category of fields.

Abstract: A communication method includes: a network device sends first configuration information to a terminal device, where the first configuration information includes configuration information of a non-anchor carrier; and when an anchor carrier is in a standalone deployment mode, the non-anchor carrier uses an in-band deployment mode or a guard-band deployment mode; or when an anchor carrier is in an in-band deployment mode or a guard-band deployment mode, the non-anchor carrier uses a standalone deployment mode.

Abstract: A system for indexing animated content receives detections extracted from a media file, where each one of the detections includes an image extracted from a corresponding frame of the media file that corresponds to a detected instance of an animated character. The system determines, for each of the received detections, an embedding defining a set of characteristics for the detected instance. The embedding associated with each detection is provided to a grouping engine that is configured to dynamically configure at least one grouping parameter based on a total number of the detections received. The grouping engine is also configured to sort the detections into groups using the grouping parameter and the embedding for each detection. A character ID is assigned to each one of the groups of detections, and the system indexes the groups of detections in a database in association with the character ID assigned to each group.

Abstract: Through a workflow interface, a document management system enables a user to establish a document workflow. The document workflow establishes a set of document actions for the document management system to perform automatically in response to a request from the user. The user defines the document workflow by selecting from a set of workflow operations and specifying parameters for the selected workflow operation. The user additionally defines an approval workflow operation and a rejection workflow operation that designate document actions in the event that a document is approved or rejected, respectively. The document management system performs at least a portion of the document workflow in an order determined from the workflow interface.

Abstract: A service application programming interface (API) invoking method where a security method applied to an API exposing function entity is updated from an original security method to a new security method, and where the security method of the API exposing function entity is used for communication between the API exposing function entity and an invoker. The method includes: obtaining, by the invoker, a new security method of the API exposing function entity; and sending, by the invoker, a first invoking request to the API exposing function entity using the new security method, where the first invoking request includes a name of a service API, and where the first invoking request is used to invoke the service API.

Abstract: Systems and methods for configuring a medical record generation platform are provided. A first graphical user interface comprising a visual representation of a natural-language statement structure is displayed, and a first input comprising an instruction to update the natural-language statement structure to specify a first aspect of patient medical information is received. In response to receiving the first input, display of the visual representation is updated to include a visual representation of the first aspect of patient medical information, and an option group region representing a set of options for describing the first aspect is displayed. In accordance with the first user input, a data structure is stored comprising instructions for providing a platform for generating a natural-language healthcare document conforming to the natural-language statement structure represented by the visual representation, wherein the natural-language statement specifies the first aspect of patient medical information.

Abstract: The present disclosure relates to a document comparison system (100) for comparing a first document (D1) with a second document (D2). The first document (D1) includes at least a first section having at least one first section entity (CEn), and the second document (D2) includes at least one second document entity (CEn). The document comparison system includes a processor (110) and a memory device (120). The processor is configured to identify the at least one first section entity (CEn) in the first section of the first document (D1). The processor conducts a search of the second document (D2) to identify the presence or absence of one or more second document entity (CEn) corresponding to or equivalent to each first section entity (CEn) identified in the first section. The present disclosure also relates to a dictionary generating system; a document comparison method; a dictionary populating method; and non-transitory computer-readable medium.

Abstract: Provided herein is a method of generating and communicating map version agnostic road link identifiers. Methods may include: receiving an indication of a new road link being joined to an existing road link along a length of the existing road link, where the existing road link extends between a first node and a second node, where the existing road link has a first road link identifier, and where a new node is formed where the new road link joins the existing road link; generating a first new identifier for a segment of the existing road link between the first node and the new node; generating a second new identifier for a segment of the existing road link between the new node and the second node, where the second new identifier is set equal to an XOR function of the first road link identifier and the first new identifier.

Abstract: A new ecosystem monitoring solution provides novel features including a dashboard service, a dashboard notifier, and a near real time query processor. The dashboard service can continuously aggregate, through the dashboard notifier and optionally dashboard agents, metadata from disparate ecosystem components of a complex computing platform or ecosystem. The metadata include metrics of crawling, data ingestion, and content enrichment activities and health information of the disparate ecosystem components. The metrics are processed with respect to a time window utilizing an expression tree dynamically constructed by the query processor. The query processor can navigate the expression tree to form collection models. Each collection has aggregation functions for aggregating a set of metrics specified in a view model.

Abstract: File annotation is described. An example method includes: processing files to be annotated by using an annotation model to determine a first performance of the annotation model, the first performance being associated with the confidence of a model annotation result generated by the annotation model; if the first performance is lower than a predetermined threshold, determining a group of target files from the files based at least on the confidence of the model annotation result; acquiring truth-value annotation information of the group of target files for retraining the annotation model; and if a second performance of the retrained annotation model is higher than or equal to the predetermined threshold, determining annotation information for at least some of the files by using the retrained annotation model. Based on this approach, automatic annotation of files can be realized with less truth-value annotation information, thereby reducing annotation costs.

Abstract: A device and method for a website building system that has a component based version comparer to compare at least two versions of a website page which has components defined in a set of hierarchies. The components can be a visual component, a container and a non-visual site element. The device generates a difference tree representing the differences in the components between two versions of the website page using the version comparer to preprocess the components in a version of a website page to determine internal geometric and semantic relationships before comparing the components and the relationships between the two versions using semantic and geometrical analysis. The device also includes a version merger to create an integrated version of the two versions of the website page according to the difference tree.

Abstract: The present disclosure is directed towards systems and methods for extracting structure and headers from a body of text. This computational extraction is based on the visual and logical similarities between portions of text. Boilerplate is removed from chunks of text making up potential headers and the cleaned result is compared against other potential headers and the remainder of the body of text.

Abstract: System for converting a spreadsheet in a first format to a second format comprising: a server including a storage means adapted to store the spreadsheet in the second format and store an associated template; a data set associated with the spreadsheet in the second format, such that the data set is adapted to be associated with the template to be displayed on a client device; and wherein when data is associated with the template, changes made via the client device to the associated data is recorded in realtime in both the spreadsheet in the second format and template. A process for generating an output for a webpage, comprising: selecting a spreadsheet and a template stored by a server, the spreadsheet comprising a data set; associating the data set with an element in the template, such that when the data is associated with the template, changes made to the associated data is recorded in realtime in both the spreadsheet and template; and generating the output comprising the data associated with the template.

Abstract: Systems and methods for creating, inserting, and managing a field. The field comprising a key and a corresponding formula. The key and the formula of the field stored in a database of a field management system. The method for inserting the field including receiving a field insertion request; identifying and forwarding, by the field management system, one or more keys and formulas corresponding to one or more suggested fields for rendering on a user interface of a client device; receiving, at the field management system, indication of selection of a key from the one or more keys; computing, by the field management system, a result for the formula of the field associated with the selected key; and communicating the result from the field management system to the first client application for rendering in line with the electronic content.

Abstract: The invention relates to computer-implemented systems and methods for assessing the quality of a document or a technical memorandum written with a loosely defined template, stereotype and/or outline of key sections or headers. An embodiment of the present invention leverages Natural Language Processing (NLP) and Machine Learning (ML) techniques to identify key sections in a document using NLP text patterns and further establish, using ML, how closely a given section matches similar sections in other documents that are considered by human Subject Matter Experts (SMEs) to be “well-written” for the intended purpose of the overall document. An embodiment of the present invention further ascertains whether the overall flow of the document follows a general outline in terms of the order of sections.

Abstract: A non-transitory computer-readable recording medium stores a design document management program causing a computer to execute a process including: acquiring a plurality of design documents about a system; identifying a plurality of label items representing elements of the system based on appearance frequency information of character strings included in the plurality of design documents acquired; and generating structure information in which the plurality of label items are hierarchized based on appearance positions at which the character string corresponding to each of the plurality of label items identified appears in the plurality of design documents.

Abstract: Data (e.g., security data) is presented at increasing levels of detail in a drill down on graphical displays. The data can be retrieved pursuant to a request, such as a search. A first graphical display corresponds to a first level of the detail. A first actionable graphic is displayed, which, when activated, presents a second graphical display with more detail. Thus, nested graphical displays are provided. The detailed data may be retrieved in response to a search, with only the high-level data graphically displayed first, with the additional data and stored templates be ready to instantly produce the nested, detailed charts upon use activation.

Abstract: A computer-implemented method is provided. The method comprises: receiving, from a text field of a user interface, input text strings containing medical data; identifying, based on language semantics and grammatical structure, a keyword and one or more data values from the input text strings; providing the keyword as an input to a query of a medical data category database to obtain one or more categories associated with the keyword, the one or more categories including a first category; retrieving, from a template database, a first template associated with the first category, the first template including one or more fixed blocks and one or more variable blocks; inserting a data value corresponding to the keyword into a variable block of the first template to generate a replacement text string; and displaying the replacement text string in place of the input text strings in the text field.

Abstract: An information processing apparatus includes a display controller for displaying a first display window which is displayable with a second display window in a display screen in a superposed manner, and an input obtaining unit for obtaining a user's input for moving the first display window in the display screen. The display controller changes, when a user's input for moving the first display window toward an outside of the display screen is obtained in a first display state in which the first display window is displayed in the display screen, a state of the first display window to a second display state in which the first display window is displayed in a region at an end of the display screen in accordance with a direction of the movement of the first display window.

Abstract: A document authoring platform receives a user-selected idea type attribute of a structured document template. The platform identifies a supporting idea type attribute based on the user-selected idea type attribute and taxonomy rules for the structured document template. The platform receives a user-selected supporting idea type attribute and content of the user-selected supporting idea type attribute. The platform forms a tree structure of the structured document template based on the user-selected idea type attribute, the user-selected supporting idea type attribute, and the content of the user-selected supporting idea type attribute. A document is generated based on the tree structure.

Abstract: A computer-implemented method, apparatus and program product use the spatial locations of words identified in an unstructured document to both reconstruct lines in the unstructured document and vertically partition the unstructured document. Key/value pairs may then be generated from one or more of the reconstructed lines by using one or more words to one side of the vertical partition as keys and using one or more words to the other side of the vertical partition as values.

Abstract: The disclosed technology creates a family of spreadsheet functions (predefined formulas) which allows users to create programming loop equivalents in their regular spreadsheet cells combining familiar range or array evaluating functions (e.g., SUM, COUNT, MIN, MAX, etc.) with data filtering and output selection. The input data to these new functions can be sourced from multiple cells within the spreadsheet or a broad spectrum of numeric, date and text data not stored in a spreadsheet, including data not discretely defined. The technology disclosed can use as inputs cell ranges or Non-spreadsheet Cell (NSC) data formulas. The technology supports functions with predefined combinations and user specified combinations all capable of automating, millions of looped calculations.

Abstract: There is provided an image archiving method for use with a writing target, comprising the steps of receiving a series of captured images of the writing target, detecting difference between first and second candidate received images separated by a predetermined period of time, where additive differences are indicative of writing and subtractive differences are indicative of erasure; upon detecting subtractive difference, temporarily retaining a last candidate image captured prior to the detection, and detecting whether the subtractive difference relative to the retained image exceeds a subtraction threshold amount; and if so, then storing the retained image.

Abstract: A graphical user interface (GUI) (or a user navigation interface), is a common feature of computer systems and application well known to one having ordinary skill in the arts. In cloud service broker (CSB) environments, GUI rendering is more complicated because independent software vendors (ISV) distribute cloud applications (cloud services) through CSBs and allow different cloud applications to collaborate through standardized representational state transfer (RESTful) application program interfaces (API). If there are multiple applications that are integrated, the GUI may include numerous interfaces specifically tailored to the each of the specific applications. However, preparing all combinations of screens requires extensive development, which increases as more and more applications are integrated.

Abstract: Systems and methods for managing content items of the type used in Web sites. In accordance with the disclosure, site objects, channel objects and content objects are associated with each other to form a hierarchical site structure. The content objects are linked to corresponding content items in a content repository, and are grouped together by association with channel objects in the site structure. Each of the objects in the site structure has an associated set of content services and can be deployed individually or in combination, while maintaining references to the related objects in the hierarchical site structure.

Abstract: Font recommendation systems and techniques are provided for determining one or more font recommendations. Content aware font recommendations can be determined for an electronic document based on information from the design context of the electronic document. For example, to generate recommended fonts for an electronic document, the font recommendation systems and techniques can obtain one or images of the electronic document and/or text from the electronic document as input, and can process the one or more images and/or the text to determine recommended font tags. In some cases, recommended fonts can be determined based on user search queries, such as when a user searches for a particular font.

Abstract: A system comprising: one or more processors; and program instructions for providing a user interface. Execution of the program instructions by the one or more processors causes the one or more processors to display a user interface comprising: an entry mechanism for entering an input comprising at least one character, symbol, numeral or punctuation mark; a typing pane configured to display the input entered via the entry mechanism; wherein, in response to selection of a prediction based on the input entered via the entry mechanism, the typing pane is configured to replace the input entered via the entry mechanism by the prediction; and an undo button, wherein in response to user selection of the undo button, the typing pane is configured to replace the selected prediction by the input entered via the entry mechanism.

Abstract: Systems and methods for linking a data set to respective locations of relevant data elements in documents included in electronic files in which a formatting server identifies a specific location of each occurrence of each of a plurality of different categories of fields in documents in an electronic file and links an identifier of each of the categories to each specific location of each of the occurrences. Thereafter, a review server compares data populating all of the occurrences at each specific location of at least one of the categories of fields to which the identifier of the particular category of fields is linked and generates a notification when the data populating any of the occurrences differs from data populating any of the other occurrences of the same category of fields.

Abstract: Systems and methods are provided for enhancing text-based electronic communications. In one embodiment, a sending agent automatically, or upon request by a user, disambiguates identifiers and terms included in a communication internally or in collaboration with a remote device or server based on the identity and history of the sending or intended receiving device or user, the content or context of the communication and/or the sending or intended receiving device or user and automatically or at the request of the sender, appends, enhances or provides certain additional information related to the identifier or terms to the message in real time. This additional information is then included or referenced, but not necessarily initially displayed or communicated, in the communication. The integrated system also may include a receiving agent on the receiving device that can disambiguate the identifier or terms and provide additional information and services related to the identifier or terms in the communication.

Abstract: An artificial document generation method generating a larger set of artificial documents which mimics a smaller set of source documents. The method may include deriving metadata parameters from source documents, each parameter characterizing the source documents and having more than one possible value. The deriving may include: determining which ratio of the source documents has each of the values, defining metadata ratios characteristic of the source documents; training a model, on the source documents, to output artificial documents; and running the model as trained thereby to output artificial documents and overriding at least some words generated by the model in the draft artificial documents. Overriding is configured to ensure that at least some of the ratios characteristic of the smaller set of source documents are retained in the larger set.

Abstract: Interfaces and systems are provided for harvesting ground truth from forms to be used in training models based on key-value pairings in the forms and to later use the trained models to identify related key-value pairings in new forms. Initially, forms are identified and clustered to identify a subset of forms to label with the key-value pairings. Users provide input to identify keys to use in labeling and then select/highlight text from forms that are presented concurrently with the keys in order to associate the highlighted text with the key(s) as the corresponding key-value pairing(s). After labeling the forms with the key-value pairings, the key-value pairing data is used as ground truth for training a model to independently identify the key-value pairing(s) in new forms. Once trained, the model is used to identify the key-value pairing(s) in new forms.

Abstract: Exposing parameters in referencing worksheets including receiving a request for a referencing worksheet linked from a data source worksheet, wherein the data source worksheet is a presentation of a data set from a database, and wherein the data source worksheet comprises a function utilizing an exposable parameter; generating the referencing worksheet from the data source worksheet, wherein the referencing worksheet exposes the exposable parameter without exposing the function utilizing the exposable parameter; and presenting the referencing worksheet with the exposable parameter without allowing access to the function utilizing the exposable parameter.

Abstract: One aspect relates to a system that integrates a user interface of a device with a cloud based database system without use of a database application. A user may access a cloud based database system without the complexity of installing additional software or managing connections to the cloud based database system. The system may establish a communication link between the user interface and intelligent agents running on the database system in order to allow a user(s) to carry out various database monitoring and verification activities.

Abstract: One or more lines of computer code are accessed. An electronic dictionary file is retrieved in response to the accessing of the computer code. The electronic dictionary file contains definitions for a plurality of commands or terms associated with the one or more lines of computer code. Based on the definitions contained in the electronic dictionary file, the one or more lines of computer code are parsed. An output is generated based on the parsing of the computer code. The output contains information explaining the one or more lines of computer code or an intended result of an execution thereof.

Abstract: A method for processing an electronic document (ED) to infer a sequence of section headings in the ED. The method includes generating, by a computer processor, based on regular expression matching of a predetermined section heading pattern and a plurality of characters in the ED, a list of candidate headings in the ED; generating, by the computer processor and based on the list of candidate headings, a list of chain fragments for inferring a portion of the sequence of section headings; and generating, by the computer processor and based on predetermined criteria, the sequence of section headings by merging at least two chain fragments in the list of chain fragments.

Abstract: The present disclosure relates to a document comparison system (100) for comparing a first document (D1) with a second document (D2). The first document (D1) includes at least a first section having at least one first section entity (CEn), and the second document (D2) includes at least one second document entity (CEn). The document comparison system includes a processor (110) and a memory device (120). The processor is configured to identify the at least one first section entity (CEn) in the first section of the first document (D1). The processor conducts a search of the second document (D2) to identify the presence or absence of one or more second document entity (CEn) corresponding to or equivalent to each first section entity (CEn) identified in the first section. The present disclosure also relates to a dictionary generating system; a document comparison method; a dictionary populating method; and non-transitory computer-readable medium.

Abstract: A system and method for linking management requirements for financial instruments to source documents. The system generates a viewing interface for viewing managed accounts that contain various financial instruments. Source documents for the financial instruments are converted into a digital format, therein producing digitized documents. The digitized documents are stored in a searchable database. The digitized documents are analyzed to locate specific clauses within the digitized documents that create management requirements. The clauses are identified with unique numerical identifiers. The numerical identifiers are used to create hyperlinks for recalling said clauses from the database. The hyperlinks are added to the viewing interface wherein the hyperlinks can be used to recall and review the clauses directly.

Abstract: Computer-implemented methods for allowing users to specify interactive graphical designs are provided. The graphical designs can comprise multiple dimension versions—such as a tablet dimension version or a phone dimension version. Some of the methods involve an inheritance structure that defines a first dimension version of the design as a child of a second dimension version of the design. Specifications for properties of widgets in the graphical design are applied to the design in accordance with the inheritance specification. Some of the methods involve an inheritance characterization that determines how properties of a widget are affected by the inheritance structure across different dimension versions. Some of the methods involve an existence property for the widgets.

Abstract: There is provided an image archiving method for use with a writing target, comprising the steps of receiving a series of captured images of the writing target, detecting difference between first and second candidate received images separated by a predetermined period of time, where additive differences are indicative of writing and subtractive differences are indicative of erasure; upon detecting subtractive difference, temporarily retaining a last candidate image captured prior to the detection, and detecting whether the subtractive difference relative to the retained image exceeds a subtraction threshold amount; and if so, then storing the retained image.

Abstract: A sharing extension point receives a request from a host application for sharing content, the sharing extension point being one of the extension points of an extension framework of an operating system, each corresponding to a common interface to extend a predefined functionality of one application to another application. In response, a sharing extension capable of providing content sharing services is launched. Data representing a share sheet created by the sharing extension is injected into a content viewer within the host application as a share sheet clone, where the share sheet clone has a reduced resolution image of the content displayed therein. In response to receiving a commit command for sharing, the actual content is retrieved from the host application and the retrieved content is transmitted to the sharing extension to enable the sharing extension to post the share sheet on a sharing platform.

Abstract: A word processing system has a keyboard having a plurality of letter keys and a shift key operable to generate capitalized letters, a processor connected to the keyboard and a display connected to the processor. The processor is operable to detect entry of an entered two-letter word, to determine if the entered two-word is in all capital letters, and if the entered two-word is in all capital letters to assess whether the typing was intentional or in error. If it is assessed that the typing was in error, the processor being operable to correct the two-letter word to an initial capital followed by a lower case letter.

Abstract: In implementations of systems for simultaneously modifying multiple variable fonts, a computing device implements a modification system to identify a first range of values of a glyph attribute that are adjustable by changing values of a particular design axis of a first variable font that is common to the first variable font and a second variable font. The modification system identifies a second range of values of the glyph attribute that are adjustable by changing values of the particular design axis of the second variable font. An overlapping range of values of the glyph attribute is determined between the first range of values and the second range of values. The modification system generates an additional instance of the first variable font and an additional instance of the second variable font for display in a user interface based on the overlapping range of values of the glyph attribute.

Abstract: A real-time analytical database system allows queries on data obtained from a transactional system that is frequently updated by the transactional system. The real-time analytical database system receives change logs from the transactional system. The change logs describe operations performed by the transactional system. The real-time analytical database system stores a plurality of indexes in a key-value store, each index comprising key-value pairs. A key of a key-value pair is obtained by combining field data describing a field of a document. The real-time analytical database system determines modifications to the key-value pairs of the key-value store corresponding to the operations of the transactional system as represented by the received change logs. The real-time analytical database system receives and processes queries using the plurality of indexes.

Abstract: Some embodiments provide a program that receives a request to sectionize a document, uses a visual model to identify a set of candidate section headers in the document, and uses a language model to determine a type of section header for at least one candidate section header in the set of candidate section headers in the document. Some embodiments provide a program that receives a request to anonymize data in a document, uses a visual model to identify a set of candidate confidential sections in the document that are each predicted to include a collection of confidential data, uses a language model to identify terms in each candidate confidential section that are determined to be confidential data, analyzes the document to identify a set of terms in the document based on the identified terms in the set of candidate confidential sections, and redacts the set of terms in the document.

Abstract: The preset disclosure provides a text editing method and a mobile terminal. The method includes: detecting a touch operation of a user on at least one text block displayed in an operating region of a preset text recycling window; and if a preset first touch operation is detected, pasting at least one character selected by the first touch operation to the current position of the cursor in a text editing region; wherein at least one text block to be recycled is stored in the text recycling window.

Abstract: Methods, systems, and apparatus, including an apparatus for using probabilistic techniques to provide reformatted versions of digital components. In one aspect, a process includes obtaining data specifying a distribution parameter limit for a given reformattable digital component that is eligible for reformatting using a set of digital component extensions. For each of multiple digital component requests, a determination is made that a given digital component extension has an additional selection requirement that, when combined with a base selection requirement for the given reformattable digital component, would exceed the distribution parameter limit.

Abstract: A system is configured to automatically enhance user content by dynamically generating alternative layouts given an original layout of the user content. The alternative layouts are generated based on determined roles for a number of different content elements on a canvas and/or detected semantic relationships between content elements. Once the alternative layouts are generated, the system can evaluate the alternative layouts and assign a score to each of the alternative layouts. The system can then identify recommended alternative layouts that are suitable for a particular purpose (e.g., a professional presentation, a teaching lesson, etc.), and provide the recommended alternative layouts for display on a device of a user.

Abstract: This disclosure provides a method for two-dimensional indication in viewing contents. The method comprises in one embodiment displaying a content page in a content display window, wherein at least one of length and width of the content page exceeds the size of the content display window. The method further comprises in one embodiment displaying indicators located at four corners of the content display window, wherein each of the indicators indicates the size of part of the content page that is outside the corresponding corner of the content display window. The method further comprises in one embodiment in response to detecting a user operation that moves the content page relative to the content display window, changing each of the indicators to reflect the current size of part of the content page that is outside the corresponding corner of the content display window.

Abstract: A method, computer system, and computer program product for generating a multi-document summary is provided. The embodiment may include receiving a query statement, one or more documents, one or more summary constraints, and quality goals. The embodiment may include identifying one or more keywords within the query statement. The embodiment may include performing a sentence selection from the one or more documents based on the one or more identified keywords. The embodiment may include generating a plurality of candidate summaries of the one or more documents based on the performed sentence selection, the goals, and a cross entropy method. The embodiment may include calculating a quality score for each of the plurality of generated candidate summaries using a plurality of quality features. The embodiment may include selecting a candidate summary from the plurality of generated candidate summaries with the highest calculated quality score that also satisfies a quality score threshold.