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: This disclosure relates generally to long-form answer extraction and, more particularly, to long-form answer extraction based on combination of sentence index generation techniques. Existing answer extractions techniques have achieved significant progress for extractive short answers; however, less progress has been made for long form questions that require explanations. Further the state-of-art long-answer extractions techniques result in poorer long-form answers or not address sparsity which becomes an issue longer contexts. Additionally, pre-trained generative sequence-to-sequence models are gaining popularity for factoid answer extraction tasks. Hence the disclosure proposes a long-form answer extraction based on several steps including training a set of generative sequence-to-sequence models comprising a sentence indices generation model and a sentence index spans generation.

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: This disclosure relates generally to long-form answer extraction and, more particularly, to long-form answer extraction based on combination of sentence index generation techniques. Existing answer extractions techniques have achieved significant progress for extractive short answers; however, less progress has been made for long form questions that require explanations. Further the state-of-art long-answer extractions techniques result in poorer long-form answers or not address sparsity which becomes an issue longer contexts. Additionally, pre-trained generative sequence-to-sequence models are gaining popularity for factoid answer extraction tasks. Hence the disclosure proposes a long-form answer extraction based on several steps including training a set of generative sequence-to-sequence models comprising a sentence indices generation model and a sentence index spans generation.

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: 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: 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: 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: Existing software defect text categorization approaches are based on use of supervised/semi-supervised machine learning techniques, which may require significant amount of labeled training data for each class in order to train the classifier model leading to significant amount of human effort, resulting in an expensive process. Embodiments of the present disclosure provide systems and methods for circumventing the problem of dependency on labeled training data and features derived from source code by performing concept based classification of software defect reports. In the present disclosure, semantic similarity between the defect category/type labels and the software defect report(s) is computed and represented in a concept space spanned by corpus of documents obtained from one or more knowledge bases, and distribution of similarity values are obtained.

Abstract: The present subject matter discloses system and method for tagging set of text snippets with set of tags. A set of text snippet and set of tags are received as input by the system. Further, each tag comprises set of words, and for each word of the set of words, numeric weight is assigned based on frequency of the word and headword of the set of words. Further, same words and similar meaning words are determined from the tag and text snippets. Further, belief factor is computed for the tag by applying certainty factor algebra upon the numeric weight assigned to the same words and the similar meaning words. Further, the tag is assigned to the text snippet based on comparison of the belief factor with threshold. Further, feedback is received about the tagging done. Based on the feedback, knowledge base of the system may be updated for future tagging.

Abstract: Existing software defect text categorization approaches are based on use of supervised/semi-supervised machine learning techniques, which may require significant amount of labeled training data for each class in order to train the classifier model leading to significant amount of human effort, resulting in an expensive process. Embodiments of the present disclosure provide systems and methods for circumventing the problem of dependency on labeled training data and features derived from source code by performing concept based classification of software defect reports. In the present disclosure, semantic similarity between the defect category/type labels and the software defect report(s) is computed and represented in a concept space spanned by corpus of documents obtained from one or more knowledge bases, and distribution of similarity values are obtained.

Abstract: Disclosed is a system for rectifying a typographical error in a text file. The system includes a network generating module for generating a linguistic network of a plurality of words present in the text file. A computation module configured to compute the similarity between each pair of words based on a set of parameters. A weight assignment module for assigning a weight to the edge present between the each pair of words based the set of parameters. A categorization module configured to categorize one or more words present in the linguistic network in a category. A word identification module configured to identify a reference word from the category. A word substitution module configured to substitute each word of the category deemed as erroneous with corresponding reference word for rectifying the typographical error.

Abstract: The present subject matter relates to method(s) and system(s) to rank human profiles based on selection criteria personalized to a selector. In an embodiment, the method includes obtaining querying criteria from the selector to query a database comprising a set of human profiles. Further, a subset of human profiles is determined from the set of human profiles based on the querying criteria and a default ranking mechanism. Furthermore, a selection based ranking is obtained for the subset of human profiles. Further, based on the selection based ranking, a ranking function is determined that is indicative of a relative inclination of the selector towards the one or more implicit attributes. Such a determination is by capturing at least one implicit attribute in the ranking function from the selection based ranking. Further, the ranking function is applied to rank a fresh set of human profiles based on the ranking function.

Abstract: The present subject matter discloses system and method for tagging set of text snippets with set of tags. A set of text snippet and set of tags are received as input by the system. Further, each tag comprises set of words, and for each word of the set of words, numeric weight is assigned based on frequency of the word and headword of the set of words. Further, same words and similar meaning words are determined from the tag and text snippets. Further, belief factor is computed for the tag by applying certainty factor algebra upon the numeric weight assigned to the same words and the similar meaning words. Further, the tag is assigned to the text snippet based on comparison of the belief factor with threshold. Further, feedback is received about the tagging done. Based on the feedback, knowledge base of the system may be updated for future tagging.

Abstract: Disclosed is a system for rectifying a typographical error in a text file. The system includes a network generating module for generating a linguistic network of a plurality of words present in the text file. A computation module configured to compute the similarity between each pair of words based on a set of parameters. A weight assignment module for assigning a weight to the edge present between the each pair of words based the set of parameters. A categorization module configured to categorize one or more words present in the linguistic network in a category. A word identification module configured to identify a reference word from the category. A word substitution module configured to substitute each word of the category deemed as erroneous with corresponding reference word for rectifying the typographical error.

Abstract: The present subject matter relates to method(s) and system(s) to rank human profiles based on selection criteria personalized to a selector. In an embodiment, the method includes obtaining querying criteria from the selector to query a database comprising a set of human profiles. Further, a subset of human profiles is determined from the set of human profiles based on the querying criteria and a default ranking mechanism. Furthermore, a selection based ranking is obtained for the subset of human profiles. Further, based on the selection based ranking, a ranking function is determined that is indicative of a relative inclination of the selector towards the one or more implicit attributes. Such a determination is by capturing at least one implicit attribute in the ranking function from the selection based ranking. Further, the ranking function is applied to rank a fresh set of human profiles based on the ranking function.