Microsoft Technology Licensing, LLC

Kevin Roland Powell

Domenic J Cipollone

Ali Taleghani

Maria Del Mar Gines Marin

Ravi Chandru Shahani

Theresa Ann Estrada

Douglas W Potter

Michael Wilson Daniels

Kylan Matthew Nieh

Kathryn V J Sullivan

Andrea Maria Jessee

Tev'n J Powers

Saliha Azzam

Shikha Devesh Desai

Kevin William Humphreys

Yizheng Cai

Lei Wang

Robert Andrew Little

William Ramsey

David Neal Weise

James P Finnigan

Michael V Calcagno

Sonja Sabina Knoll

Kaushik Ramaiah Narayanan

Pär Jonas Barklund

Susan Michele Hendrich

Siarhei Alonichau

Olivier Gauthier

Alfredo R Arnaiz

Evelyne Viegas

Kyle Matthew Von Haden

Leah Joy Brown

Patricia M Schmid

Curtis E Huttenhower

Amy Tremper

Paul Rustam Karimov

Kevin Field

Jason S Hamilton

Miriam R Eckert

Rene J Valdes

Kevin Michael Black

Laura Licari

Sean Aubrey Oldridge

Status-based reading and authoring assistance is provided. A status-based reading and authoring assistance feature can automatically determine a status of a user and automatically adapt reading and authoring tools provided for display based on the determined status. The status-based reading and authoring assistance feature provides the right reading and authoring tools at the right time, according to the current use of the application. During a user session with respect to a productivity application that includes status-based reading and authoring assistance, signals (e.g., user actions and context information) associated with a file can be received. A status regarding the use of the file can be determined using at least the signals. The status can comprise a reading status or an authoring status (or even a sub status). Reading and authoring tools provided for a display of the productivity application can be adapted based on the status during the user session.

Status-based reading and authoring assistance

A system and method includes dividing content of an electronic document into components. A document type of the electronic document is identified by comparing a document score against a document type criterion, the document score being based on a combination of a component score of each of the components. A user interface provides an indication of the document type.

Electronic document content augmentation

A system and method includes receiving content of an electronic document having a document type, the content divided into components each having a unique identifier and selecting an extraction schema based on the document type, the extraction schema having a plurality of data categories. For each of the components, the extraction schema is applied to identify content of the component that corresponds to individual ones of the data categories and saving, with the processor, in an electronic data storage, in a record associated with the component, category metadata indicative of content of the component corresponding to the data categories. In response to obtaining the category metadata for each of the components, applying the extraction schema to the content metadata of each of the components and to the electronic document as a whole to determine document metadata. A user interface displays the document metadata on the user interface.

Electronic document content extraction and document type determination

A system and method includes receiving an electronic document having content divided into components and, for each of the components, comparing content of the component with component content characteristics of a classification schema associated with a document type and storing, in an electronic data storage, in a record associated with the component, indications of the component content characteristics of the classification schema that are included in the component. Document content characteristics of the classification schema are compared with the content of the electronic document and storing, in the electronic data storage, in a record for the electronic document, indications of the document content characteristics of the classification schema that are included in the electronic document. The electronic document is identified as the document type based on the content characteristics of the records meeting a document type criteria.

Electronic document content classification and document type determination

Techniques for automatic proofing of textual data is described. In one embodiment, these techniques are directed towards producing proofed textual data for various operational environments via logic operative on a logic circuit to access information comprising a set of n-grams, at least one mapping between at least one replacement n-gram and a corresponding n-gram in the set of n-grams, and a corresponding confidence score for each mapping being determined by user activity while producing text for various applications; process input to a productivity application comprising textual data and identify a portion thereof to replace based upon the accessed information; and automatically modify the portion of the textual data using a replacement n-gram selected from the replacement n-grams based upon a corresponding confidence score between the portion of the textual data and the replacement n-gram. Other embodiments are described and claimed.

Techniques for automatic proofing of textual data

A system and method includes obtaining content extracted from an electronic document, the electronic document having a document type. At least some of the content is transmitted to an online social networking system based on the document type. A recommended content change is received from the online social networking system. A user interface dynamically displays the recommended content change concurrently with display of the electronic document as the electronic document is updated.

Potential linguistic errors within a sequence of words of a sentence are identified based on analysis of a configurable sliding window. The analysis is performed based on an assumption that if a sequence of words occurs frequently enough within a large, well-formed corpus, its joint probability for occurring in a sentence is very likely to be greater than the same words randomly ordered.

Linguistic error detection

Tools and techniques are described for providing multi-lingual word hyphenation using inductive machine learning on training data. Methods provided by these techniques may receive training data that includes hyphenated words, and may inductively generate hyphenation patterns that represent substrings of these words. The hyphenation patterns may include the substrings and hyphenation codes associated with characters occurring in the substrings. The methods may receive induction parameters applicable to generating the hyphenation patterns, and may store the hyphenation patterns into a language-specific lexicon file. These methods may also receive requests to hyphenate input words that occur in a human language, and may evaluate how to process the request based on the language. The methods may search for hyphenation patterns occurring in the input words, with the hyphenation patterns being stored in the lexicon file. Finally, the methods may respond to the request, indicating whether the hyphenation patterns occurred in the input words.

Multi-lingual word hyphenation using inductive machine learning on training data

A system and methods of language identification of natural language text are presented. The system includes stored expected character counts and variances for a list of characters found in a natural language. Expected character counts and variances are stored for multiple languages to be considered during language identification. At run-time, one or more languages are identified for a text sample based on comparing actual and expected character counts. The present methods can be combined with upstream analyzing of Unicode ranges for characters in the text sample to limit the number of languages considered. Further, n-gram methods can be used in downstream processing to select the most probable language from among the languages identified by the present system and methods.

Efficient language identification

A data structure for a word lexicon includes a plurality of separate data sections for storing information related to word entries. An indices section includes pointers indicating the location of the information. The location of the associated pointers for each word entry is obtained as a function of a list of the word entries.

Lexicon with sectionalized data and method of using the same

A method of determining the component words of a compound word is disclosed. The method identifies the component words, by comparing the word with a list of words found in a lexicon. If the word is not found in the lexicon the method proceeds to analyze the word on a character-by-character basis. After each character the method identifies any potential matches to the selected characters in the lexicon. If a match is found, it is added to a hypothesis trace in a lattice. Next, the method checks to see whether the remaining characters form a valid entry in the lexicon, and whether the entry is allowed to be a final segment.

Compound word breaker and spell checker

A lexicon stored on a computer readable medium and used by language processing systems. The lexicon can store word information in a plurality of data fields associated with each entered word. The data fields can include information on spelling and grammar, parts of speech, steps that the entered word can be transformed into another word, a word description, and a segmentation for a compound word. Information that cannot be stored in the lexicon can be stored in an intermediate indexes table. Associated methods of constructing, updating and using the lexicon are introduced.

Full-form lexicon with tagged data and methods of constructing and using the same

The present invention provides an interface and associated object model that exposes a comprehensive set of natural language processing features to an application developer. In one embodiment, the features include lexicon management services and proofing services.

Natural language processing interface

A computer-readable medium stores a first lexicon data structure for lexicon words. The first data structure includes a host form variant field containing a host form variant such as a clitic host form variant, a host form field containing the host form of the host form variant (only present if the forms differ) such as a clitic host verbal form, and a verification field indicative of whether the host form variant is a valid word. The first data structure also includes a segment association field containing data or segmentation bits associating the host form variant with certain types of attachment entries in the lexicon, which also contain data or segmentation bits, to define valid combinations between the host form variant and at least one of the attachment entries in the lexicon. A second lexicon data structure for each of the attachment entries in the lexicon is also stored.

System and method for performing analysis on word variants

Growing community of inventors

Kirkland, WA, United States of America

Kevin Roland Powell