Abstract: Described herein are systems and methods to enable generation of high-quality summaries of documents that have questions and answers. To help summarize such documents, parsing methods are disclosed that account for different document formats. Methods are disclosed to anonymize personal and identifying information present in the documents. An ontology is defined to categorize dialog acts for the questions and answers present. Classifiers are disclosed based on this ontology. Methods are also disclosed to transform a question-answer pair to a canonical form. Based on the dialog acts for the question and answer combination, transformation methods were developed that build upon each of traditional NLP, and deep learning, techniques.

Abstract: Described herein are systems and methods to enable generation of high-quality summaries of documents that have questions and answers. To help summarize such documents, parsing methods are disclosed that account for different document formats. Question-answer groups are transformed into declarative sentences. Sentence correction can be applied to the declarative sentences. Candidate summary sentences are identified from the declarative sentences, and a subset of the candidate summary sentences are selected for inclusion in a summary. Aspects, segmentation, and augmentation can help with generation and tailoring of summaries.

Abstract: Described herein are systems and methods to enable generation of high-quality summaries of documents that have questions and answers. To help summarize such documents, parsing methods are disclosed that account for different document formats. Methods are disclosed to anonymize personal and identifying information present in the documents. An ontology is defined to categorize dialog acts for the questions and answers present. Classifiers are disclosed based on this ontology. Methods are also disclosed to transform a question-answer pair to a canonical form. Based on the dialog acts for the question and answer combination, transformation methods were developed that build upon each of traditional NLP, and deep learning, techniques.