Lucent Technologies Inc.

Nuance Communications, Inc.

Palo Alto Research Center Inc.

Peter Frederick Patel-Schneider

Adwait Ratnaparkhi

Deepak Ramachandran

Lori Alperin Resnick

Peter Yeh

William Jarrold

Deborah L McGuinness

Benjamin Douglas

Johan De Kleer

Ion Matei

David L Martin

Peter Zei-Chan Yeh

Alexandre Perez

Diane Judith Litman

Ron Zvi Stern

James Melton Crawford, Jr

Daniel L Dvorak

Jan Noessner

Anil K Mishra

A method includes receiving a subject-matter expert (SME) interpretable model. The method further includes converting, by a processing device, the SME interpretable model into a functional mockup unit (FMU). The method further includes integrating the FMU into a control software project (CSP). The method further includes compiling the CSP into binary code.

Machine-learning framework for testing feedback controller robustness

In some natural language understanding (NLU) applications, results may not be tailored to the user's query. In an embodiment of the present invention, a method includes tagging elements of automated speech recognition (ASR) data based on an ontology stored in a memory. The method further includes indexing tagged elements to an entity of the ontology. The method further includes generating a logical form of the ASR data based on the tagged elements and the indexed entities. The method further includes mapping the logical form to a query to a respective corresponding database stored in the memory. The method further includes issuing the query to the respective corresponding databases. The method further includes presenting results of the query to the user via a display or a voice response system.

System and method for natural language driven search and discovery in large data sources

According to some aspects, a method for aligning a first data source and a second data source during a plurality of iterations comprising a current iteration and a previous iteration is provided. The method comprises generating at least one property alignment hypothesis between at least one first property of the first data source and at least one second property of the second data source; generating a plurality of instance alignment hypotheses between a respective first plurality of instances of the first data source and a respective second plurality of instances of the second data source; and verifying at least one property alignment hypothesis and/or at least one of the plurality of instance alignment hypotheses. Generating the at least one property alignment hypothesis and/or generating the plurality of instance alignment hypotheses is based, at least in part, on at least one property alignment hypothesis and/or at least one instance alignment hypothesis verified during the previous iteration.

Methods and system for iteratively aligning data sources

Presenting natural-language-understanding (NLU) results can include redundancies and awkward sentence structures. In an embodiment of the present invention, a method includes, responsive to receiving a result to a NLU query, loading a matching template of a plurality of templates stored in a memory. Each template has mask fields associated with at least one property. The method compares the properties of the mask fields of each of the templates to properties of the query and properties of the result, and selects the matching template. The method further completes the matching template by inserting fields of the result into corresponding mask fields of the matching template. The method may further suppress certain mask fields of the matching template to increase brevity and improve the naturalness of the response when appropriate based on the results of the NLU query. The method further presents the completed matching template to a user via a display.

A knowledge representation system which allows a user to utilize a description language to generate, maintain and access information in a knowledge base is disclosed. The knowledge representation system includes an explanation subsystem which explains where the derived information that is stored for a particular object was obtained from. A first level explanation function will provide a user with an explanation of the immediate source of the pieces of derived information that are stored for an object in the knowledge base. A complete explanation function provides a complete explanation by continuing to explain how the immediate source for each piece of the information itself received the information, until the source of the information is told information or the result of a rule firing. The explanation subsystem also explains subsumption inferences, which explain why a particular concept or rule antecedent is satisfied by a particular object. The explanation that is generated may be limited in a number of ways in accordance with the needs of a user. An error handling subsystem facilitates the detection of the source of real errors. Upon the detection of a real error, an error object is preferably created for the inconsistent object and for every other object that is affected by the error. The error objects, which may be printed out or explained, store all of the information associated with the corresponding object at a time when the data structures include the error information.

Knowledge base management system with enhanced explanation of derived

Techniques for integrating rules into imperative object-oriented languages such as C++. C++ is extended to permit definition of rules as members of classes. When a rule is defined as a member of a class, a preprocessor receives the declaration of the rule's class and of any other class involved in the rule and generates additional data members and member functions for the classes. The additional members of the classes permit a complete implementation of the rule. No additional rule interpreter or decision network is required. The rule definition defines collections of objects linked by interobject pointers to which the rule applies. A rule is evaluated only if there is a change in a value mentioned in the rule in an object belonging to a collection of objects for the rule. The rule's condition is a sequence of bindings and tests. The bindings define a path through a collections of objects to which the rule applies, and the path is followed during evaluation. The rules thus implement access-limited logic.

Integrating rules into object-oriented programming systems

A knowledge representation system which allows a user to generate, maintain and access information in a knowledge base using a description language is disclosed. The knowledge representation system maintains the dependency relationships between the different objects that are stored in the knowledge base so that pieces of information that are related to or dependent upon added or updated information may be properly classified at all times. The knowledge representation system includes a mechanism for processing dependency information that is returned from user-defined test functions in order to accurately maintain the dependency information implicated upon execution of the user-defined procedural test functions. A subsumption function determines if a particular individual in the knowledge base satisfies a concept. The subsumption function evaluates each component of a concept description and maintains the dependency information implicated by the concept component. A test restriction evaluation subroutine determines whether test restriction components of the concept are satisfied and processes the dependency information that is returned from the user-defined procedural test functions.

Knowledge base management system with dependency information for

Growing community of inventors

Westfield, NJ, United States of America

Peter Frederick Patel-Schneider