XML ABSTRACTIVE SUMMARY APPROACH

Summary Structures for XML

CrowdSummary: Crowdsourced Abstractive Summary Generation with an Intelligent Interface

A well-written abstractive summary can save readers much time and effort in comprehending the information in an extensive document. However, abstractive summary generation is a task that is difficult for both humans and computers. For humans, it takes ample time for one to digest all of the information in a document and select important sentences that can be used to generate the abstract. On th...

An Abstractive approach to Question Answering

Question Answering has come a long way from answer sentence selection, relational QA to reading and comprehension. We move our attention to abstractive question answering by which we facilitate machine to read passages and answer questions by generating them. We frame the problem as a sequence to sequence learning where the encoder being a network that models the relation between question and p...

Fully Abstractive Approach to Guided Summarization

This paper shows that full abstraction can be accomplished in the context of guided summarization. We describe a work in progress that relies on Information Extraction, statistical content selection and Natural Language Generation. Early results already demonstrate the effectiveness of the approach.

A Quantitative Summary of XML Structures

Statistical summaries in relational databases mainly focus on the distribution of data values and have been found useful for various applications, such as query evaluation and data storage. As xml has been widely used, e.g. for online data exchange, the need for (corresponding) statistical summaries in xml has been evident. While relational techniques may be applicable to the data values in xml...