Abstract: A data processing system implements receiving textual content from a first application on a first client device associated with a first user for analysis by a writing assistant configured to provide suggestions for improving the textual content. The textual content is analyzed by one or more NLP models configured to receive the textual content as an input and to provide candidate suggestions for correcting errors and/or otherwise improving the textual content. The candidate suggestions are associated with a suggestion category, and a determination is made by an autocorrection model whether autocorrection is appropriate for the suggestion category. The textual content is autocorrected based on those candidate suggestions for which autocorrection is appropriate while the remainder of the candidate suggestions may be presented to the user for approval prior to applying the candidate suggestions to the textual content.

Abstract: A computer implemented method includes receiving text corresponding to a span of text. Language detection is performed on the received text to generate multiple language candidates. The received text is also proofed over multiple languages to generate multiple language proofing critiques. A most likely language is generated for the received text as a function of the language candidates and the multiple language proofing critiques.

Abstract: Techniques for providing annotations in a web browser or a native application herein include analyzing the structure of a webpage to determine a topology, constructing a model of the webpage based on the topology configured to automatically monitor the topology and to update the model based on detected changes to the webpage, extracting, from the model, a first text string from textual content of a first editable node, sending at least first portion of the first text string to a server to obtain annotations, detecting that the textual content of the first editable node has been modified by a second text string modifying at least a portion of the textual content, receiving the annotations from the server comprising suggestions for improving the first text string, updating the annotations to produce reconciled annotations by modifying the annotations, and rendering the reconciled annotations over the first editable node.

Abstract: Techniques for providing annotations in a web browser or a native application herein include analyzing the structure of a webpage to determine a topology, constructing a model of the webpage based on the topology configured to automatically monitor the topology and to update the model based on detected changes to the webpage, extracting, from the model, a first text string from textual content of a first editable node, sending at least first portion of the first text string to a server to obtain annotations, detecting that the textual content of the first editable node has been modified by a second text string modifying at least a portion of the textual content, receiving the annotations from the server comprising suggestions for improving the first text string, updating the annotations to produce reconciled annotations by modifying the annotations, and rendering the reconciled annotations over the first editable node.

Abstract: Techniques for providing writing assistance features a web browser or a native application including an embedded web browser herein include detecting that a webpage has been rendered by the web browser; analyzing a structure of the webpage to determine a topology of the webpage by accessing a Document Object Model (DOM) of the webpage and traversing the DOM of the webpage to identify nodes comprising the webpage to determine the topology of the webpage; construct a model of the webpage based on the topology, wherein the model of the webpage is configured to automatically monitor the topology of the webpage and to update the model based on detected changes to the webpage; detect, using the model, a change in textual content of an input element of the webpage; obtain annotation information associated with the textual content; and render the annotations over at least a portion of the webpage.

Abstract: Enhanced spelling correction is provided. An enhanced spelling correction service may determine any misspellings (e.g., a word of the text containing an identified spelling error) in text using lexicon-based spelling correction. Each misspelling is assigned an error flag. The service can communicate each misspelling to a language model-based spell checker and receive, for each misspelling, an error confidence signal from the language model-based spell checker. For each misspelling having an error confidence signal indicating a low confidence that the identified spelling error is an actual spelling error, the service can determine whether to maintain or suppress the error flag by applying decision logic. In response to determining to maintain the error flag, the service can surface a visual indication of the spelling error. In response to determining to suppress the error flag, the service can suppress the error flag whereby the visual indication of the spelling error is not surfaced.

Abstract: An electronic system provides financial advice based on personal data and financial objectives entered by users, by means of a rules engine. The rules engine detects whether the financial objectives match the personal data provided by the user and issues a challenge, or initiates a communication with a financial adviser, if they do not. The system stores general financial information and automatically provides updated financial advice to the user when the general financial information changes. The financial advice is in the form of a document compiled from text passages selected by matching predefined values to the user's personal data. The data and rules used to generate the financial advice are stored so as to be available for inspection, to demonstrate compliance with financial regulations.