Tata Consultancy Services Limited

Other

Smita Subhash Ghaisas

Preethu Rose Anish

Abhishek Sainani

Manish Motwani

Shirish Subhash Karande

Shashi Kant Sharma

Manasi Samarth Patwardhan

Richa Sharma

Aarthy Krishnamurthy

Balaji Balasubramaniam

This disclosure relates generally to data processing, and more particularly to a method and system for generating ground truth labels for ambiguous domain specific tasks. The system generates reference data corresponding to a regulation statement being processed, using a crowd sourcing mechanism and then processes the reference data using an Expectation Maximization (EM) model. The EM model determines consensus with respect to ambiguity of terms/phrases, validity of questions, and validity of answers, and then based on the determined consensus, provides questions and answers to disambiguate the regulation statement.

Method and system for generating ground truth labels for ambiguous domain specific tasks

Resolving ambiguities in regulatory documents is necessary to ensure organizations and people are able to be best possible compliant with regulations or standards. Current approaches attempting to automatically resolve ambiguities in regulatory documents have limitations when it comes to incorporating fairness or reduce chances of subjective interpretation. Embodiments of the present disclosure provide a method and system for automatically resolving ambiguities in regulations. To disambiguate a given regulatory sentence the method augments the regulation sentence with relevant internal information extracted using a set of predefined linguistic patterns and relevant external information extracted from external sources identified using a Neural Network (NN) model. The augmented text comprising the regulation sentence, the relevant internal information and the summarized relevant external information enables the end user to make an informed interpretation of the regulation sentence and resolve ambiguity present in the regulation sentence.

Method and system to resolve ambiguities in regulations

The present subject matter relates to an automated classification of business rules. In one embodiment, a method for automated classification of the business rules comprises identifying a business rule from a text document, wherein the business rule comprises one or more rule intents. Further, the method comprises comparing the one or more rule intents in the business rule with rule intents associated with a plurality of rule types in a rule repository. Furthermore, the method comprises classifying the business rule under at least one of the rule types based on the comparison.

Automated classification of business rules from text

A system(s) and method(s) for identifying project requirement are described herein. The system identifies the architecturally significant functional requirements from the functional requirements from a client/customer. The system further classifies the identified architecturally significant functional requirements into specific classes based on the architectural impact they may have on the project. Subsequently, the system generates a meta schema related to architecturally significant functional requirements based on the classification of architecturally significant functional requirements and pre-defined schema. Thereafter, system recommends the specific probing questions from the bank of probing questions to unearth unspecified or underspecified architecturally relevant information based on the generated meta schema. The system further recommends architectural solutions selected from a bank of architectural solutions based on answers received for specific probing questions in response to the architectural impact they may have on the project.

Computer implemented system and method for identifying project requirements

Systems and methods for automated interpretation of legal regulations are described. The described systems implement a method that includes receiving a plurality of legal regulations and deconstructing the plurality of legal regulations based on at least one of a regulatory rule model and Minsky's frames to form a computer interpretable regulation repository. The method also includes identifying rule intents applicable to each of the deconstructed plurality of legal regulations; and classifying the plurality of legal regulations into at least one rule act based at least on the identified rule intents.

Systems and methods for an automated interpretation of legal regulations

Methods and systems described herein implement a recommendation system for providing recommendations for generating a requirements specification for agile software development. In one implementation, the system includes a processor and a memory coupled to the processor. The memory comprises a mapping module and an agile recommendation module. The mapping module is configured to map knowledge elements of at least one ontology instance selected from among a plurality of ontology instances with another ontology instance selected from among the plurality of the ontology instances. The agile recommendation module is configured to generate a knowledge corpus based on the mapped knowledge elements of the ontology instances and at least one environmental parameter, receive modifications in the knowledge corpus, and provide recommendations to generate a requirements specification based at least, in part, on the received modifications.

Growing community of inventors

Pune, India

Smita Subhash Ghaisas