Xerox Corporation

Conduent Business Services, LLC

Claude Roux

Denys Proux

Stefania Castellani

Frederic Roulland

Caroline Brun

Aaron N Kaplan

Julien Perez

Antonietta Grasso

Bernard Jacquemin

Tracy Eugene Thieret

Donald J Gusmano

Gregory T Grefenstette

Jean-Yves Vion-Dury

Eric Gaussier

Jacki O'Neill

Jean-Pierre Chanod

Roger T Kramer

Ronald M Rockwell

Caroline Hagege

Salah Ait-Mokhtar

Frederique Segond

Caroline Hagège

Diana Nicoleta Popa

Christophe Servan

Karin Pettersson

A method and method for natural language generation employ a natural language generation model which has been trained to assign an utterance label to a new text sequence, based on features extracted from the text sequence, such as parts-of-speech. The model assigns an utterance label to the new text sequence, based on the extracted features. The utterance label is used to guide the generation of a natural language utterance, such as a question, from the new text sequence. The system and method find application in dialog systems for generating utterances, to be sent to a user, from brief descriptions of problems or solutions in a knowledge base.

Natural language generation, a hybrid sequence-to-sequence approach

A method for supervising text includes receiving input text in a natural language, the input text including at least one source sentence. The input text is analyzed, which includes, for a source sentence in the input text, generating a syntacetic representation. A target sentence is generated in the same natural language, based on the syntacetic representation. The source sentence is compared with the target sentence to determine whether there is a match. A decision is output, based on the comparison.

Authoring system

Systems and methods for aspect-based opinion mining including identifying the polarity (e.g., positive, negative, etc.) of different features of a product or a service as expressed in a text. This general task can be divided into four sub-tasks: identifying the aspect terms, classifying them into one of a set of predefined aspect categories, and identifying the polarity of the aspects terms and the aspect categories. A combination of systems (e.g., rule-based and machine learning based) can be employed to implement aspect category and aspect term polarity mutual annotation for aspect-based sentiment analysis.

Category and term polarity mutual annotation for aspect-based sentiment analysis

A method for aspect categorization includes receiving an input text sequence and identifying aspect terms and sentiment phrases in the input text sequence, where present. For an identified aspect term, identifying sentiment dependencies in which the aspect term is in a syntactic dependency with one of the identified sentiment phrases, and identifying pseudo-dependencies from a dependency graph of the input text sequence. The dependency graph includes a sequence of nodes. In a pseudo-dependency, a node representing the aspect term precedes or follows a node representing a semantic anchor in the dependency graph without an intervening other aspect term. Features for the aspect term are extracted from at least one of identified sentiment dependencies and identified pseudo-dependencies. With a classifier trained to output at least one of category labels and polarity labels for aspect terms, classifying the identified aspect term based on the extracted features.

Loose term-centric representation for term classification in aspect-based sentiment analysis

A method for generating a natural language response to a customer inquiry includes parsing sentences in a corpus of natural language dialogs between a respective customer and an agent to extract dependencies. Each parsed sentence is represented by a dependency graph, based on the extracted dependencies. Dependency templates are generated, at least some of which are each generated from two or more of the extracted dependency graphs (e.g., using variables which each represent a group of words referring to a same topic) and are stored in a knowledge base. In response to the customer inquiry, one of the stored dependency templates is identified and a natural language response to the inquiry is generated, using the identified dependency template. The natural language response is generated based on words extracted from the natural language dialogs that are linked, in memory, to the identified dependency template.

System and method for response generation using linguistic information

A method, a system, and a computer program product for processing search queries are disclosed. A first query pertaining to a primary theme is received. One or more secondary queries are then generated. Each of the one or more secondary queries is associated with a corresponding plausible secondary theme. The first query and the one or more secondary queries are then submitted to a search engine.

Method and system for processing search queries

A system and method for assisting a user to enter data are provided. The method includes detecting a user's selection of a moveable input zone on each of one or more input documents displayed on the user's screen and detecting a user's selection of a moveable target zone on a target document displayed on the user's screen. Data in the input zone(s) and the target zone is captured for one or more locations of the respective zones and a pattern is learned automatically for filling additional data in the target document based on the captured data. A fill arrangement for filling the additional data in the target document based on the learned pattern is generated, which can be presented to the user for validation.

Smart macros using zone selection information and pattern discovery

A system, method, and storage medium for generating visual content in plural versions for substantially simultaneous display on the same display device are provided. The system includes memory for storing static content having at least one document element common to a first and second version of a document, multi-dimensional content having at least one customized document element for each document version to be inserted into a variable area within the first and second versions of the document, and multi-dimensional parameters defining static areas, variable areas, and customized document elements for each document version. The system further includes a rendering module adapted to generate a first frame-image corresponding to the first document version and a second frame-image corresponding to the second document version by arranging the static content and multi-dimensional content of each document version according to the multi-dimensional parameters.

Multi-dimensional documents for parallel content display on a single screen for multiple viewers

A system for retrieval of text includes a processor which identifies grammar rules associated with text fragments of a text string that is retrieved from an associated storage medium, and retrieves text strings from the storage medium which satisfy the grammar rules. A display displays retrieved text strings. A user input device in communication with the processor enables a user to select text fragments of the displayed text strings for generating a query. The processor identifies grammar rules associated with the user-selected text fragments and retrieves text strings from the storage medium which satisfy the grammar rules.

Linguistic user interface

A method for troubleshooting a problem with a device includes acquiring device data for the device, receiving a user's query concerning a device in a natural language, presenting possible refinements to at least a portion of the user's query for defining a problem statement, presenting candidate solutions that are associated with the defined problem statement in a knowledge base, at least one of the presentation of possible refinements and the presentation of candidate solutions being informed by device data that is linked through a diagnostic model of the device to at least one of the problem statements and candidate solutions.

Informing troubleshooting sessions with device data

A linguistic rewriting rule for use in linguistic processing of an ordered sequence of linguistic tokens includes a token pattern recognition rule that matches the ordered sequence of linguistic tokens with a syntactical pattern. The token pattern recognition rule incorporates a character pattern recognition rule to match characters contained in an ambiguous portion of the ordered sequence of linguistic tokens with a character pattern defining a corresponding portion of the syntactical pattern.

Bi-dimensional rewriting rules for natural language processing

A system suited to self-troubleshooting includes a processor which identifies normalized forms of at least some of the words of a natural language user query input by a user. The user query may describe a problem experienced with a machine, such as a printer. The processor retrieves text strings which may comprise problem statements stored in memory. Each retrieved problem statement includes at least one word with a normalized form which is recognized by the processor as being equivalent to one of the identified normalized forms. Each of the retrieved problem statements may be associated with at least one solution sequence for addressing the problem with the machine. In the event that the stored problem statements in memory are not fully responsive, the processor provides one or more options for refinement of the user query based on tags associated with those words of the problem statements which are responsive.

Natural language processing for developing queries

A computer retrieval system includes memory which stores instructions for (1) receiving a user query in a natural language, (2) identifying text strings from an associated knowledge base, each containing at least one expression (word or multi-word expression) which is matched with at least one expression of the user query, (3) refining the user query by representing at least a group of the text strings as a navigation tree in which each of a plurality of selectable nodes comprises an expression representative of at least one syntactic unit in at least one of the identified text strings and wherein relationships between syntactic units are used in structuring the nodes of the navigation tree, and (4) retrieving text from the knowledge base related to the refined query. A processor executes the instructions.

Navigation system for text

Systems and methods for indexing and searching the inner structure of a string over a language having a vocabulary and a grammar using bit vectors. The index preserves the inner gramatical structure of the string while allowing for a fast search. A single search provides immediate access to every level of a document, without having to re-search a single string to determine which sub-parts of that string match the search string. When a string is indexed, the index maintains a compositional representation and the grammatical relationship between the elements of the vocabulary according to the language. The string is then indexed on different levels by disregarding some of the grammatical relationships of component levels.

Systems and methods for indexing each level of the inner structure of a string over a language having a vocabulary and a grammar

The present invention provides a method and a parser for syntactically analyzing an input string. The parser applies a plurality of rules which describe syntactic properties of the language of the input strings. The plurality of rules comprise two types of rules. A first type of rules comprises immediate dominance rules and linear precedence rules. A second type of rules being sequence rules. All rules of the plurality of rules are applied according to a predefined order to the input string. This new incremental parsing architecture has advantages with respect to grammar engineering and allows a more efficient parsing.

Growing community of inventors

Grenoble, France

Claude Roux