Tata Consultancy Services Limited

Girish Keshav Palshikar

Sachin Sharad Pawar

Rajiv Radheyshyam Srivastava

Sangameshwar Suryakant Patil

Vasudeva Varma Kalidindi

Pushpak Bhattacharyya

Swapnil Vishveshwar Hingmire

Nitin Vijaykumar Ramrakhiyani

Manoj Madhav Apte

Indrajit Bhattacharya

Abhay Sodani

Anindita Sinha Banerjee

Soham Datta

Harsimran Bedi

Rahul Ramesh Kelkar

Harrick Mayank Vin

Mangesh Sharad Gharote

Shailesh Shankar Deshpande

Amrish Shashikant Pathak

Sandeep Chougule

Prabir Mallick

Savita Suhas Bhat

Sharmishtha Prakash Kulkarni

Kripabandhu Ghosh

Devavrat Shailesh Thosar

Samiran Pal

Avinash Kumar Singh

Yash Agrawal

Akshada Ananda Shinde

Sriram Baskaran

Sushodhan Sudhir Vaishampayan

Amol Madhukar Aaeer

Anil Kumar Kurmi

Deepak Pandita

Ankita Jain

Apoorv Shrivastava

Ravina Vinayak More

Sangemeshwar Suryakant Patil

Aditi Anil Pawde

Athiappan G

Pragati Hiralal Dungarwal

Swapnil Vishweshwar Hingmire

Saheb Chourasia

Swapnil Vishbeshwar Hingmire

This disclosure relates generally to extraction of cause-effect relation from domain specific text. Cause-effect relation highlights causal relationship among various entities, concepts and processes in a domain specific text. Conventional state-of-the-art methods use named entity recognition for extraction of cause-effect (CE) relation which does not give precise results. Embodiments of the present disclosure provide a knowledge-based approach for automatic extraction of CE relations from domain specific text. The present disclosure method is a combination of an unsupervised machine learning technique to discover causal triggers and a set of high-precision linguistic rules to identify cause/effect arguments of these causal triggers. The method extracts the CE relation in the form of a triplet comprising a causal trigger, a cause phrase and an effect phrase identified from the domain specific text. The disclosed method is used for extracting CE relations in biomedical text.

Method and system for extraction of cause-effect relation from domain specific text

This disclosure relates to extraction of tasks from documents based on a weakly supervised classification technique, wherein extraction of tasks is identification of mentions of tasks in a document. There are several prior arts addressing the problem of extraction of events, however due to crucial distinctions between events-tasks, task extraction stands as a separate problem. The disclosure explicitly defines specific characteristics of tasks, creates labelled data at a word-level based on a plurality of linguistic rules to train a word-level weakly supervised model for task extraction. The labelled data is created based on the plurality of linguistic rules for a non-negation aspect, a volitionality aspect, an expertise aspect and a plurality of generic aspects. Further the disclosure also includes a phrase expansion technique to capture the complete meaning expressed by the task instead of merely mentioning the task that may not capture the entire meaning of the sentence.

Extraction of tasks from documents using weakly supervision

The method and system of the present disclosure facilitate automatic, and in an objective manner, selection of an optimal set of technical questions, from a question bank, personalized for a candidate. This ensures consistent, standardized, efficient and objective interviews that result in high quality recruitment, given the diversity of candidates, complexity of job requirements and interviews are inherently subjective. The state-of-the-art depends on responses so far, to generate on-the-fly questions causing a cognitive load on the interviewer. Also, there is no guarantee on the breadth and depth of concepts assessed in each interview. In the present disclosure, skill graphs are employed to create a semantically rich and detailed characterization of questions in terms of concepts. Optimization formulation uses the skill graph to generate constraints, content balancing and objective functions for selection of questions.

Integer linear programming based generation of a personalized optimal questionnaire using a skill graph

Questions play a central role in assessment of a candidate's expertise during an interview or examination. However, generating such questions from input text documents manually needs specialized expertise and experience. Further, techniques that are available for automated question generation require input sentence as well as an answer phrase in that sentence to generate question. This in-turn requires large training datasets consisting tuples of input sentence answer-phrase and the corresponding question. Additionally, training datasets are available are for general purpose text, but not for technical text. Present application provides systems and methods for generating technical questions from technical documents. The system extracts meta information and linguistic information of text data present in technical documents. The system then identifies relationships that exist in provided text data. The system further creates one or more graphs based on the identified relationships. The created graphs are the used by the system to generate technical questions.

Automated systems and methods for generating technical questions from technical documents

Financial audits establish trust in the governance and processes in an organization, but they are time-consuming and knowledge intensive. To increase the effectiveness of financial audit, present disclosure provides system and method that address the task of generating audit recommendations that can help auditors to focus their investigations. Adverse remarks, financial variables mentioned in each sentence are extracted/identified from audit reports and category tag is assigned accordingly, thus creating a knowledge base for generating audit recommendations using a trained sentence classifier. In absence of labeled data, the system applies linguistic rule(s) to identify adverse remark sentences, and automatically create labeled training data for training the sentence classifier. For a given financial statement and financial variables in the audit report that contribute to suspiciousness, the system compares these with the extracted knowledge base and identify aligned adverse remarks that help auditor(s) in focusing on specific directions for further investigations.

Identifying and categorizing adverse remarks from audit reports for knowledge base creation and generating recommendations

Extracting data from documents is challenging due to the variation in structure, content, styles across geographies and functional areas. Further complex relation types are characterized by one or more of N-ary entity mention arguments, cross sentence span of entity mentions for a relation mention, missing entity mention arguments and entity mention arguments being multi-valued. The present disclosure addresses these gaps in the art to extract entity mentions and relation mentions using a joint neural network model including two sequence labelling layers which are trained jointly. The mentions are extracted from documents to facilitate downstream processing. A first RNN layer creates sentence embeddings for each sentence in the document being processed and predicts entity mentions. A second RNN layer predicts labels for each sentence span corresponding to a relation type. Using predefined rules, entity mentions for each entity type are selected for extracting relation mentions from the identified sentence spans.

Extracting mentions of complex relation types from documents by using joint first and second RNN layers to determine sentence spans which correspond to relation mentions

This disclosure relates generally to retrieval of prior court cases using witness testimonies. Conventional state-of-the-art methods use supervised techniques for answering basic questions in legal domain using numerous features and do not address interpretability of results and the performance and precision of retrieving prior court cases for these methods are less. Embodiments of the present disclosure obtains an embedded representation for an event structure of a user query and testimony sentences identified from prior court cases using a trained Bi-LSTM classifier and a set of linguistic rules. A similarity is estimated between the embedded representation for the event structure of the user query and the event structure of each testimony sentence from the prior court cases. Further a relevance score is assigned in accordance with the estimated similarity to retrieve the relevant prior court cases. The disclosed method is used to retrieve the relevant prior court cases using witness testimonies.

Method and system for retrieval of prior court cases using witness testimonies

The present disclosure provides a system and method for recommending context and sequence aware based training set to a user. The system identifies various items and keywords of a plurality of earlier trainings of the users' interest and generates a context and sequence aware recommendation model based on the context of the identified keywords. It uses a collapsed Gibbs Sampling as in generative modelling for prior trainings. Further, it applies the context and sequence aware recommendation model on various keywords that are of users' interest. The context and sequence aware recommendation model infers a plurality of subsequent trainings based on context derived from the keywords. In addition to this, the model is generated to rank the inferred plurality of subsequent topics using a probability distribution over subsequent keywords. At the last, it recommends at least one topic to the user based on ranking of the plurality of trainings.

System and method for context and sequence aware recommendation

Narrative texts contain rich knowledge about actors and interactions among them. It is often useful to extract and visualize these interactions through a set of inter-related timelines in which an actor has participated. Current approaches utilize labeled datasets and implement supervised techniques and thus are not suitable. Embodiments of the present disclosure implement systems and methods for automated extraction of Message Sequence Chart (MSC) from textual description by identifying verbs which indicate interactions and then use dependency parsing and Semantic Role Labelling based approaches to identify senders (initiating actors) and receivers (other actors involved) for these interaction verbs. The present disclosure further employs an optimization-based approach to temporally re-order these interactions.

Automated extraction of message sequence chart from textual description

Event prediction system and method includes gathering data corresponding to multiple entities to derive multiple entity profiles. Next, a first subset of entity profiles is identified from the multiple entity profiles generated. The identification is done on the basis of characteristics associated with the entities. Subsequent to identification of the first subset of the entity profiles, a second subset of entity profiles is shortlisted. Here, the second subset of entity profiles shows highest probability of occurrence of the event. Further, a determination of a factor that may lead to occurrence of the event is done.

Event prediction system and method

System and method for automatic entity relationship (ER) model generation for services as software is disclosed. ER model generation by automated knowledge acquisition is disclosed, and automation of knowledge generation process is disclosed. Information extraction process is automated and multilevel validation of information extraction process is provided. System comprises training module to train information extraction model, and knowledge generation module for population of ER model. Standard Operators are generated based on the ER model so generated (populated). Context aware entity extraction is implemented for the ER model generation. System and method leverages existing ER model to make the system self-learning and intelligent, and provides common platform for knowledge generation from different data sources comprising documents, database, website, web corpus, and blog.

Method and system for entity relationship model generation

To evaluate performance of organizational units using Human Capital Value (HCV), the input data spread across an enterprise may be received from a user. The input data includes employee data, project related data, and organizational unit data for performance evaluation. The input data is analyzed for generating HCV variables. The HCV variables are stored in a repository (). Further, the HCV variables may be parsed to determine an optimal set of variables. Based on the parsing, an efficiency of each organizational unit is computed. The computing is based on a Multi Criteria Decision Analysis (MCDA) technique. Based on the computing, the organizational units are ranked in a decreasing order of efficiency.

Evaluating performance of organizational units using human capital values

Text analysis, specifically, narratives, wherein identification of distinct and independent participants (entities of interest) in a narrative is an important task for many NLP applications. This task becomes challenging because these participants are often referred to using multiple aliases. Identifying aliases of participants in a narrative is crucial for NLP applications. Existing conventional methods are supervised for alias identification which requires a large amount of manually annotated (labeled) data and are also prone to errors. Embodiments of the present disclosure provide systems and methods that implement Markov Logic Network (MLN) to encode linguistic knowledge into rules for identification of aliases for aliases mention identification using proper nouns, pronouns or noun phrases with common noun headword.

Markov logic networks based alias links identification and canonical mention selection in text

The present invention relates to system and method for evaluating reviewer's ability to provide feedback. The system receives feedback given by the reviewer that includes qualitative feedback and quantitative feedback. The system performs scoring of qualitative feedback to evaluate level of noise, suggestions, appreciation, specificity and duplicate comments in the qualitative feedback. Further, the system performs scoring of quantitative feedback that includes realistic score, softness score and critical nature score. Subsequently, the scores of qualitative feedback and quantitative feedback are aggregated to provide a rank to the reviewer for the reviewer's ability to provide feedback.

System and method for evaluating reviewer's ability to provide feedback

This disclosure relates generally to performance appraisal management, and more particularly to standardization of goals associated with performance appraisal. In one embodiment, a method for standardization of goals includes identifying labeled and unlabeled goals associated with a role. The goals includes template and manually created goals. Each of the template goals is associated with a class label, and includes corresponding goal description and self-comments. First and second classifiers are trained using goal description and self-comments. Candidate negative goals are identified and excluded from the goals to obtain a set of unlabeled goals. The set of unlabeled goals are classified by the first and second classifier, and a confidence score associated with the classification is determined. The unlabeled goals with high confidence score are added to labeled goals to obtain an updated set of labeled goals. The first and second classifiers are iteratively co-trained using the updated set of labeled goals.

System for standardization of goal setting in performance appraisal process

Growing community of inventors

Pune, India

Girish Keshav Palshikar