Abstract: Systems and methods for performing non-statistical text analysis are provided. Essentially unconstrained natural language text may be segmented into individual terms, which are assigned a semantic category with the aid of a category lexicon and category association table. Categorized terms may be grouped into expressions if they commonly refer to a concept. Terms, as well as information about their categories and groupings into expressions, may be organized into information blocks, which each may contain a discrete piece of information about a text. Information blocks may be used to populate a database about the text. Information blocks may be queried to answer a question, be compared to identify inconsistencies in the text, be used to identify functions to execute from a user's command, or how to respond to a user during a dialog.

Abstract: Systems and methods are directed to providing personalized text proofing. A user model that is used to personalize generic critiques for text proofing a document is generated based on user signals indicating past user actions. During runtime of an application used to create the document, the user model is accessed and locally cached. User inputs comprising typed components used to create the document are received and a set of one or more generic critiques for the user inputs is accessed from an editor system. The user model is applied to the set which may modify a generic critique of the set. The modifying of the generic critique can cause the generic critique to be automatically applied or suppressed at the client device. The set including the modified generic critique is transmitted to a user device, whereby the user device applies the set to the document including automatically applying or suppressing the modified generic critique.

Abstract: Systems and methods for improved spelling checking are disclosed. A method includes receiving a search query from a user device and determining that the search query does not exist in a data store that stores (a) a corpus of correctly spelled words or (b) forced correction mapping data. The method further includes, in response to the determining, determining a plurality of suggested search queries generated by a plurality of respective spell corrector models, selecting a suggested search query determined using a spell corrector model from the plurality of spell corrector models based on at least one of a frequency of the suggested search query in historical search data or a weightage associated with the spell corrector model, and causing the suggested search query to be displayed on the user device.

Abstract: A system for analyzing and prescribing content changes to achieve target readability level evaluates a readability score for a file at least at a whole document level and a sentence level based on a designated readability index; identifies one or more sentences that contribute to the file having the whole document level readability score outside a desired readability score of the readability index; provides a visual indicator for each of the identified one or more sentences; and re-evaluating the readability score for the file at the whole document level upon at least one of the identified one or more sentences being changed.

Abstract: A content management system obtains at least a portion of a meeting transcript based on an audio stream of a meeting attended by a plurality of users, the meeting transcript obtained in an ongoing manner as words are uttered during the meeting. The content management system detects text entered by a user of the plurality of users into a content item during the meeting. The content management system matches the detected text to at least part of the at least the portion of the meeting transcript. The content management system provides the at least part of the at least the portion of the meeting transcript to the user as a suggested subsequent text.

Abstract: Methods and electronic devices for processing a spoken utterance associated with a user of an electronic device are disclosed. The method includes generating a textual representation of the spoken utterance having words, identifying a nonce word and a non-normalized word amongst the words, and generating a plurality of candidate textual representations based on the textual representation. The candidates have at least one of a first set of candidate textual representations and a second set of candidate textual representations, such that candidates from the first set are missing the nonce word from the words of the textual representation, and candidates from the second set have the non-normalized word from the words of the textual representation replaced by a normalized version thereof. The method includes comparing the candidates against grammars, and in response to a match, triggering an action associated with the grammar.

Abstract: A quality assessment method for automatic annotation of speech data is provided and includes: building a base rule-base of automatically annotated speech data based on quality key indicators; reading automatically annotated speech data to be detected, and performing quality detection on the automatically annotated speech data to be detected according to the quality key indicators to thereby complete quality measurement; updating an automatically annotated speech dataset according to a result of the quality measurement; and importing the automatically annotated speech dataset after the updating into the base rule-base. The shortcomings of using traditional quality assessment methods for data annotation in automatic machine annotations can be overcome, and it can play a very positive supporting role in promoting the development of ethnic minority speech intelligence.

Abstract: Transactions include text fields, such as description fields. Transactions are extracted from financial institutions using web-scraping extraction. In the process of extracting transactions, errors can be introduced into text fields, such as the inclusion of a space within a word or the removal of a space between words. A statistical approach is applied to the text fields. When two alternative text fields are presented, the alternative that statistically includes more common tokens, such as unigrams and bigrams, is chosen as the correct alternative. The incorrect alternative is replaced by the correct alternative in the text field.

Abstract: A system is provided for determining a natural language output, responsive to a user input, using different speech personality profiles. The system may determine to user a particular language generation profile based at least in part on data relating to the user input and data corresponding to the response to the user input. The language generation profile may include different attributes that are used to determine the natural language output, such as, prosody, replacement words, injected words, sentence structure, etc.

Abstract: A system and method are presented for model derivation for entity prediction. An LSTM with 100 memory cells is used in the system architecture. Sentences are truncated and provided with feature information to a named-entity recognition model. A forward and a backward pass of the LSTM are performed, and each pass is concatenated. The concatenated bi-directional LSTM encodings are obtained for the various features for each word. A fully connected set of neurons shared across all encoded words is obtained and the final encoded outputs with dimensions equal to the number of entities is determined.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining a textual term; determining, by one or more computers, a vector representing a phonetic feature of the textual term; comparing the vector representing the phonetic feature of the textual term with a reference vector representing a phonetic feature of a reference textual term; and classifying the textual term based on the comparing the vector with the reference vector.

Abstract: A set of candidate edits for a word of a sentence is obtained. Each of the set of candidate edits includes an edit word. Two or more surrounding words that each have a dependency relationship with the edit word are identified in the sentence. At least one of the two or more surrounding words is identified irrespective of their proximity to the edit word. The dependency relationship between the edit word and each of the surrounding words and the set of candidate edits is provided as input to a grammar accuracy prediction model. One or more outputs of the grammar accuracy prediction model are obtained. The one or more outputs indicate grammatical accuracy of each candidate edit from the set in the sentence in view of the dependency relationship with surrounding words. The candidate edit with highest accuracy is selected from the candidate edit set for the sentence.

Abstract: The presently disclosed embodiments may include a computer readable medium including instructions that when executed by one or more processing devices cause the one or more processing devices to perform a method. The method may include: analyzing an electronic document text; identifying in the electronic document text a first drafted text element to be modified; causing the first drafted text element to be highlighted to a user on a display; generating at least one text output option that conveys a meaning associated with the first drafted text element but includes one or more changes relative to the first drafted text element; and causing the at least one text output option to be shown to the user via the display.

Abstract: There is provided an electronic device including a display, a designation device configured to designate any range of a character string displayed on the display by a user, and a processor. The processor is configured to target as a processing target at least one character included in the range designated by the designation device, determine to which of a plurality of predetermined combinations a combination of a character type of the at least one character and a position of the at least one character in the range corresponds, and execute a process on characters included in the designated range based on the determined combination.

Abstract: A voice recognition device and a method for learning voice data using the same are disclosed. The voice recognition device combines feature information for various speakers with a text-to-speech function to generate voice data recognized by a voice recognition unit, and can improve voice recognition efficiency by allowing the voice recognition unit itself to learn various voice data. The voice recognition device can be associated with an artificial intelligence module, a robot, an augmented reality (AR) device, a virtual reality (VR) device, devices related to 5G services, and the like.

Abstract: Disclosed is a system for speech recognition text enhancement fusing multi-modal semantic invariance, the system includes an acoustic feature extraction module, an acoustic down-sampling module, an acoustic feature extraction module, an acoustic down-sampling module, an encoder and a decoder fusing multi-modal semantic invariance; the acoustic feature extraction module is configured for frame-dividing processing of speech data, dividing the speech data into short-term audio frames with a fixed length, extracting thank acoustic features from the short-term audio frames, and inputting the acoustic features into the acoustic down-sampling module for down-sampling to obtain an acoustic representation; inputting the speech data into an existing speech recognition module to obtain input text data, and inputting the input text data into the encoder to obtain an input text encoded representation; inputting the acoustic representation and the input text encoded representation into the decoder to fuse.

Abstract: A method and system for providing replacement text segments for a given text segment may include receiving a request to provide the replacement text segment for the text segment in the document, examining a content characteristic of the document, and examining at least one of user-specific information, organization-specific information, or non-linguistic features of the document, before identifying at least one replacement text segment for the text segment, via a machine translation system, based on the content characteristic of the document and at least one of the user-specific information, the organization-specific information, or the non-linguistic features of the document. The method and system may include providing the identified replacement text segment for display to a user, receiving an input indicating a user's selection of the identified replacement text segment, and upon receiving the input, replacing the text segment in the document with the identified replacement text segment.

Abstract: Systems and methods are provided for facilitating the transformation of data from a tabular data set organized according to a data schema to an object based data set organized according to data ontology. The data schema and the data ontology may be used to generate a custom coding language suitable for facilitating the creation of a transform script. Error checking, type checking, autocomplete, and preview tools may be provided to permit the verification of the transform script as it is created.

Abstract: An example method includes requesting, by a user device from a remote provider and from a local provider, candidate data for use in autofill for an application. The method further includes receiving a first data set from the remote provider and a second data set from the local provider. The method additionally includes detecting that an input field of the application has focus, where the input field is included in both sets. The method further includes responsively causing a selectable list to be displayed on the user device, where the selectable list includes a first selectable option corresponding to the first data set and a second selectable option corresponding to the second data set. The method also includes receiving user input data indicating a selected data set and responsively filling one or more candidate values from the selected data set into one or more corresponding input fields of the application.

Abstract: Disclosed are methods of displaying and editing a document having editable text that allows for a wide variety of word verification features beyond merely correcting errors in spelling or grammar and allows for such detailed editing in a simple and user-friendly manner.

Abstract: A system to convert sequences of words, along with concurrent non-verbal data, into thought representations, said system being used in association with a language understanding system, where words to thought transformation is needed, is disclosed. Said system comprises: an entity look-up subsystem that comprises: a pre-processing unit, a word database, and a cache; a controller or thought representation formation and reasoning unit; a multi-word entities buffer; an entity knowledge base; a predictive word meaning memory; and an output thought representation unit.

Abstract: Provided is a method, system, and computer program product for context-dependent spellchecking. The method comprises receiving context data to be used in spell checking. The method further comprises receiving a user input. The method further comprises identifying an out-of-vocabulary (OOV) word in the user input. An initial suggestion pool of candidate words is identified based, at least in part, on the context data. The method then comprises using a noisy channel approach to evaluate a probability that one or more of the candidate words of the initial suggestion pool is an intended word and should be used as a candidate for replacement of the OOV word. The method further comprises selecting one or more candidate words for replacement of the OOV word. The method further comprises outputting the one or more candidates.

Abstract: A method for providing a review process of a document can include receiving, at a document server, the document to be reviewed from a first client; providing, by the document server, access to the document to be reviewed via a second client to start the review process for a user of the second client. During and/or after the review process, the document server can evaluate the quality of the review process and provide information on the evaluated quality to the first client so that the user of the first client can receive an indication of how the review process has occurred or is occurring and have an indication of the quality of that review that is being performed or was performed. Embodiments of a communication apparatus and system for providing information on a review process of a document can be configured to utilize embodiments of the method.

Abstract: The present disclosure relates to systems, methods, and computer-readable media for using a variety of hypothesis tests to identify errors within tables and other structured datasets. For example, systems disclosed herein can generate a modified table from an input table by removing one or more entries from the input table. The systems disclosed herein can further leverage a collection of training tables to determine probabilities associated with whether the input table and modified table are drawn from the collection of training tables. The systems disclosed herein can additionally compare the probabilities to accurately determine whether the one or more entries include errors therein. The systems disclosed herein may apply to a variety of different sizes and types of tables to identify different types of common errors within input tables.

Abstract: The following disclosure describes software components, such as add-ins, that are launched automatically, without being manually activated by a user. In some embodiments, the add-in may run silently, e.g. the add-in runs in the background, without displaying content in an ancillary pane. The add-in may be given access to document content, enabling pre-processing as well as decorating document content with metadata for future use. The add-in may determine that the document has met a criteria, and in response, display a visual cue directing the user to activate the add-in. When a user does manually activate the add-in by clicking on an icon or pressing a keyboard shortcut, the add-in may be pre-loaded, initialized, and have already accessed and processed document content. In this way, the add-in may display useful content in an ancillary pane in much less time, solving the technological problem of delay between manual activation and initialization of an add-in.

Abstract: A mechanism is provided in a data processing system comprising at least one processor and at least one memory, the at least one memory comprising instructions which are executed by the at least one processor and configure the processor to implement a document processing system. A spell check confidence component executing within the document processing system records a mapping of misspelled words to corrected words for set of documents. The spell check confidence component generates an error-to-correction frequency model based on the mapping. A parser executing within the document processing system parses an input document to extract words in the error-to-correction frequency model. The spell check confidence component calculates a precision score for each word in the input document found in the error-to-correction frequency model. The precision score represents a probability that the extracted word is spelled correctly as intended in the input document.

Abstract: A method of operating a health tracking system is disclosed. The method comprises: receiving a first data record comprising at least a first descriptive string regarding a consumable item, the first descriptive string having at least one word thereof incorrectly spelled; generating a vector using the first descriptive string using a machine learning model; identifying a second descriptive string which corresponds to the consumable item and which has a correct spelling of the at least one incorrectly spelled word by applying the machine learning model to the generated vector; calculating a confidence factor regarding the identified second descriptive string using the machine learning model; and when it is determined that the confidence factor exceeds a predetermined threshold, (i) modifying the first data record by replacing the first descriptive string with the second descriptive string, and (ii) storing the modified first data record in the database.

Abstract: A finger-mapped gesture system is a user interface method and apparatus for rapid data input on a touch-sensitive surface. The user gestures by holding the hand stationary relative to the surface and moving the fingers primarily by extension and flexion on the surface. Each finger gestures on a gesturing area instead of selecting among keys. Individual gestures are constructed from finger actions that each independently parameterize the gesture. In combination, the particular fingers gesturing and the parameters that the fingers gesture indicate the input that the user intends. On devices that do not directly identify fingers, fingers are identified via a finger map that, after calibration to a person's hand, associates each finger with a gesturing area. Gestures are otherwise independent of where they are performed, freeing users from having to look at their fingers to target visual elements. The system is optimized for rapid character data entry.

Abstract: Disclosed herein are system, method, and computer program product embodiments for generating a data structure and responding to an aggregation query. An embodiment operates by a computer implemented method that includes receiving, by at least one processor, a request to enter data in a block in a data structure. The method further includes reading, by the at least one processor, a first aggregated value stored in the data structure. The first aggregated value represents a sum over at least values associated with data that is stored in the block in the data structure. The method further includes calculating, by the at least one processor, a second aggregated value by adding the first aggregated value and a value associated with the data to be entered in the data structure. The method further includes storing, by the at least one processor, at least part of the data to be entered and the second aggregated value in the block in the data structure.

Abstract: A system, method and program product that provides user specific text suggestions across a set of hosted applications. A disclosed method includes: initiating a session with an application hosting platform for a user using a client device, wherein the platform includes a plurality of applications; accessing a dictionary associated with the user, wherein the dictionary provides text suggestions in response to inputted keyboard data and the dictionary is applicable for the user across each of the plurality of applications; deploying a selected application from the to the user at the client device; intercepting keyboard data entered by the user within the selected application; analyzing intercepted keyboard data and generating text suggestions specific to the user using the dictionary associated with the user; and outputting text suggestions within the selected application. The text suggestions are generated independently of capabilities of deployed application and operating systems running on the client device.

Abstract: The present application is directed to a system and method for creating on-line comments of a point of interest. The system and method creates a moment having a piece of digital content showing the point of interest, wherein the moment has a time stamp and a location stamp; and shares the moment with a predetermined group of members. The sharing of the moment is limited to members that meet the time stamp and the location stamp, and the system and method refuse accepting comments from members that do not meet the time stamp and location stamp.

Abstract: The invention relates to a method. The method includes receiving a flawed input comprising a domain specific misspelling. The method further includes encoding, by an encoder machine learning model executing on a computer processor, the flawed input on a per character basis to create a context vector. The method further includes decoding, by a decoder machine learning model executing on the computer processor, the context vector on the per character basis to create a rephrased input lacking the domain specific misspelling. The method further includes presenting the rephrased input.

Abstract: A method includes providing a server including a memory and a processor coupled to the memory; defining a plurality of databases in the memory, the databases including fields for respective client matters, and the databases including a plurality of notes for respective matters, the notes including text, and the databases including a plurality of buzzwords; associating respective buzzwords with descriptive pages; generating a user interface including a text editing screen area in which a user can type text for a note, the text including a plurality of terms; comparing terms to the buzzwords and, in response to a term matching a buzzword, indicating that the matching term is a buzzword in the user interface. Other systems and methods are also provided.

Abstract: In non-limiting examples of the present disclosure, systems, methods and devices for assisting with task completion are provided. A natural language input may be received. A natural language processing engine may be applied to the natural language input. A primary task associated with the natural language input may be identified. A plurality of subtasks for completing the primary task may be identified from the natural language input. A determination may be made from the natural language input that the primary task or one of the plurality of subtasks is more important than other tasks. The primary task and the plurality of subtasks may be added to a list of tasks in a task completion application. An indication of importance may be associated in the task completion application in association with the task or subtask that is determined to be more important.

Abstract: A computer-implemented method for transforming a sequence comprising multiple words from a natural language to a machine executable sequence in real-time to control a machine. The sequence constituted by multiple characters forming words from the natural language is preprocessed by comparing the sequence to data from a database comprising classes. The sequence is searched for simple expressions and GI expressions known to be an upstream function class or a downstream function class. The sequence is dichotomized until all of the function classes contained in the sequence that are capable of resulting in dichotomies have been dichotomized. The first to the last classes of the sequence are iterated and each executable class is executed by a machine.

Abstract: Transactions include text fields, such as description fields. Transactions are extracted from financial institutions using web-scraping extraction. In the process of extracting transactions, errors can be introduced into text fields, such as the inclusion of a space within a word or the removal of a space between words. A statistical approach is applied to the text fields. When two alternative text fields are presented, the alternative that statistically includes more common tokens, such as unigrams and bigrams, is chosen as the correct alternative. The incorrect alternative is replaced by the correct alternative in the text field.

Abstract: A method, computer program product, and computer system for identifying, by a computing device, a change to at least one record of a plurality of records in a multi-record update. At least one problem condition associated with the change to the at least one record is determined, wherein the at least one problem condition is determined via at least one problem definition object before the change is saved. The at least one problem condition is organized on a display. An action is executed on the at least one problem condition displayed.

Abstract: A marking assist device includes a memory, a storage that stores an image that records a competition in which a player performs a plurality of skills in a time sequence, and a processor coupled to the memory and configured to acquire a first marking result and a second marking result, the first marking result being marking of each of the plurality of skills based on sensor data on the performing player, the second marking result being inputted by a referee, display first discriminators of the skills included in the first marking result and second discriminators of the skills included in the second marking result while associating the first discriminator with the second discriminator, and when any discriminator is selected from the displayed discriminators, identify a video associated with selected discriminator from the images and displays the identified video.

Abstract: The present document describes system and method for securing a text against copying and tampering. The system introduces a reversible change within the instructions contained in the electronic page description language defining the text. In a non-limiting example, the reversible change may include replacing the font used in the PDL by a customized font defining a set of changes from the standard/existing fonts. The system may then generate a set of instructions reversing the set of changes to display the proper text to the user. However, should any tampering or illegal copying of the text occur, the original text will not be displayed because a portion of the reversible change is not present. The reversible changes introduced may affect character sizes, colors, spacing, positions, mapping etc.

Abstract: An embodiment provides a method, including: receiving, at a processor, an indication of an input including a word; providing, on a touch screen, an enlarged view of the input indicated, wherein the enlarged view is off set from an input entry field on the touch screen; and accepting, using a processor, editing input that modifies the word. Other embodiments are described and claimed.

Abstract: A method and system for correcting a mistyped word resulting from at least one of an inaccurate keyboard input and wrong keyboard layout is disclosed. The method comprises selecting a first n-characters of a first word, selecting candidate characters that are likely subsequent characters to the first n-characters by calculating a candidate score value for each candidate character; generating a respective positive reformulated word for each selected candidate characters which corresponds to the first word having replaced the n+1 character with the respective candidate character; and training a machine learning algorithm (MLA) to determine a set of features representing a property between each reformulated words and the first word; and training the MLA to determine the reformulated word having an absence of a mistype.

Abstract: A finger-mapped gesture system is a user interface method and apparatus for rapid data input on a touch-sensitive surface. The user gestures by holding the hand stationary relative to the surface and moving the fingers primarily by extension and flexion on the surface. Each finger gestures on a gesturing area instead of selecting among keys. Individual gestures are constructed from finger actions that each independently parameterize the gesture. In combination, the particular fingers gesturing and the parameters that the fingers gesture indicate the input that the user intends. On devices that do not directly identify fingers, fingers are identified via a finger map that, after calibration to a person's hand, associates each finger with a gesturing area. Gestures are otherwise independent of where they are performed, freeing users from having to look at their fingers to target visual elements. The system is optimized for rapid character data entry.

Abstract: The present invention provides an electronic document review method comprising the steps of displaying at least a first document section of said document in a first display window, displaying at least a second document section of said document in a second display window, and arranging said second window so that said second window is arranged within the border of the first window. Such a method allows for efficient review of electronic documents thereby enabling a user to reduce the amount of time the user spends for reviewing an electronic document. The invention also provides an electronic document review system.

Abstract: An apparatus, process, and computer program to prevent inappropriate messages originated from a client device is provided. A validation message that includes a message composed by a user may be received from a client device. A determination is made as to whether the composed message comprises data that matches with one or more inappropriate terms, phrases, and/or objects. A notification is sent to the client device when the composed message comprises data that matches with one or more inappropriate terms, phrases, and/or objects.

Abstract: Embodiments provide a method for detecting inappropriate content in user interactions, including: receiving an unstructured text-based input corresponding to a user interaction of a user; analyzing, using a text analytics technique, the text-based input to identify content within the input; determining whether at least a portion of the content within the input comprises inappropriate content by determining if the at least a portion of the content is categorized as inappropriate content; if the content is categorized as inappropriate content, identifying the content as inappropriate content; and if the content is not categorized as inappropriate content, receiving text-based input from other users, analyzing the text-based input from other users to determine a sentiment of the text-based input from other users, generating a content score for the content of the user, and identifying the content as inappropriate content if the content score meets or exceeds a predetermined threshold; and performing an action.

Abstract: A method and a device for converting a dialect of a predetermined language into a standard language include obtaining a sentence including a dialect word, identifying at least one common word that is used identically in the dialect and the standard language in the sentence including the dialect word, replacing the identified at least one common word with a predetermined keyword, obtaining one or more vector values corresponding to the predetermined keyword and each of remaining words included in the sentence, and obtaining a standard language sentence based on an arrangement of the obtained one or more vector values.

Abstract: A mobile terminal including a wireless communication unit configured to provide wireless communication; a display configured to display at least a first notification information at a first position on the display indicating a first event occurred on the mobile terminal, and display a second notification information at a second position on the display indicating a second event occurred on the mobile terminal; and a controller configured to in response to a selection of the first notification information, display a first input region and a first key region for inputting a character string into the first input region on the display adjacent to the first notification information, in response to a selection of the second notification information, display a second input region and a second key region for inputting the character string into the second input region on the display adjacent to the second notification information, and process the character string input into the first input region or the second input reg

Abstract: The embodiments of the present application disclose a spell checking method and device, which relate to the technical field of computer software. The method includes: determining character segments corresponding to characters contained in a page to be displayed according to preset character segment dividing rules; obtaining the character locations of wrong words in each of the determined character segments; presenting each of the determined character segments and marking wrong words in the corresponding character segment in a form of preset mark according to the character locations of wrong words in each of character segments. The solutions provided by the embodiments of the present application are applied to improve document loading speed and document displaying speed, thereby improving users' experience.

Abstract: A portable electronic device is disclosed comprising: data processing means; data repository containing data records representative of locations relevant to or within a digital map; and display means. The device further comprises means for monitoring a free text search string as it is input by a user of the device; querying the data repository for matching records and generating suggestions selectable by a user to adjust the search, based on the search string as it is input; displaying at least some of any matching records and suggestions on the display; and, in response to receipt of user input indicating a selection of a matching suggestion, adjusting the search accordingly.

Abstract: The present disclosure includes methods, apparatus, and computer-readable media for receiving one or more user inputs from a user via a user interface, transmitting the one or more user inputs to a remote server, obtaining an expected user input interval and an expected response latency, and displaying, via the user interface, either one or more predicted inputs associated with a content of a local cache or one or more predicted inputs received from the remote server, based at least on whether the expected user input interval is greater than a product of the expected response latency and a factor.