Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: This disclosure relates generally to method and system to classify news snippets into categories using an ensemble of machine learning models. The ensemble is between a bidirectional long short memory (BILSTM) based text classification network and a pretrained language model (PLM) based natural language inference (NLI) which is robust and accurate for such categorization. The method trains a first machine learning model using a training dataset to learn text representations. Further, the training dataset is used to finetune a second machine learning model to classify at least one unlabeled news snippet of unknown category based on a premise-hypothesis pair. Further, an ensemble of machine learning models is generated by using the first machine learning model and the second machine learning model to classify a set of test news snippets received as input request to corresponding category.

Abstract: Existing approaches for processing and evaluation of documents containing non-fiction narrative texts have the disadvantage that they are comparatively less studied in linguistics, and hence do not provide sufficient data required for evaluations. Method and system are for evaluating non-fiction narrative text documents are provided. The system processes a plurality of non-fiction narrative text documents and computes a plurality of corpus statistics. The plurality of corpus statistics is then used for evaluation of any non-fiction narrative text document that may or may not be collected as real-time input.

Abstract: Conventional Question and Answer (QA) datasets are created for generating factoid questions only and the present disclosure generates longform technical QA dataset from textbooks. Initially, the system receives a technical textbook document and extracts a plurality of contexts. Further, a first plurality of questions are generated based on the plurality of contexts. A plurality of answerable questions are generated further based on the plurality of contexts using an unsupervised template-based matching technique. Further, a combined plurality of questions are generated by combining the first plurality of questions and the plurality of answerable questions. Further, an answer for the combined plurality of questions are generated using an autoregressive language model and a mapping score is computed. Further, a plurality of optimal answers are selected based on the corresponding mapping score.

Abstract: This disclosure relates to the field of incident analysis, and, more particularly, to systems and methods for similarity analysis in incident reports using event timeline representations. Conventionally, processing of repositories of incident reports to identify similar incidents is challenging due to use of unstructured text data in describing the incident reports. Timeline representation is an important knowledge representation which captures chronological ordering of the events. The timeline representation becomes useful in process of root cause analysis as causes would temporally precede the effect. To construct event timeline representations, chronological ordering of events is required. The present disclosure provides a temporal relation identification technique to obtain a timeline representation of the events. Further, a similarity identification approach is used that makes use of neural embeddings to identify similar timeline representations and in turn, similar incident reports.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: This disclosure relates generally to predicting proficiency level of a person from resume. The proficiency levels obtained using state-of-the-art methods tends to overestimate proficiency. Moreover, the estimated proficiency levels do not satisfy several constraints that are considered key by subject matter experts. Embodiments of the present disclosure extract skills and other related information automatically from resume and capture skill related information in terms of a feature vector. A skill estimation function is learned to predict the proficiency level of the skill from the feature vector using any one of two models. A first model is learned using a constraint loss function to combine label information with domain specific constraints and a second model is learned using a clustering based technique. The disclosure predicts skill proficiency using only resume and can be used for predicting proficiency level of skills of employees from their resumes, for suitable job recommendations from job portal.

Abstract: This disclosure relates generally to method and system for providing assistance to interviewers. Technical interviewing is immensely important for enterprise but requires significant domain expertise and investment of time. The present disclosure aids assists interviewers with a framework via an interview assistant bot. The method initiates an interview session for a job description by selecting a set of qualified candidates resume to be interviewed. Further, the IA bot recommends each interviewer with a set of question and reference answer pairs prior initiating the interview. At each interview step, the IA bot records interview history and recommends interviewer with the revised set of questions. Further, an assessment score is determined for the candidate using the reference answer extracted from a resource corpus. Additionally, statistics about the interview process is generated, such as number and nature of questions asked, and its variation across to identify outliers for corrective actions.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: The online shopping is highly based on human perception on products and the human perception on products depends on semantic features of products. Conventional methods provides product recommendation based on historical data and are supervised. The present disclosure receives a set of multi-modal data. A plurality of features are extracted from the set of data at a plurality of resolution levels and the plurality of features are arranged as parallel corpus based on a category associated with each data from the set of data. Further, an abstract interaction vector is computed for each element of the set of data using the parallel corpus. Further, the set of recommendations are identified by comparing the abstract interaction vector associated with the set of data with an abstract interaction vector associated with each of a plurality of items stored in the database by utilizing a similarity metric.