Leveraging Syntactic Information for Coherent and Comprehensible Summarization

Abstract

Text summarization is a natural language processing problem which has been investigated by the NLP community for half a century. In the era of information explosion, the community has intensified research for more sophisticated methods for automated text summarization. Attempts were made in the past to frame extractive and abstractive techniques for multidocument summarization. Extractive techniques select a subset of sentences which can approximate the summary of the input corpus of documents, while abstractive summarization newlinetechniques construct a semantic representation and are expected to generate the summary in newlineits own learnt writing style. newlineExtractive techniques create an intermediate representation for the target text, capturing the newlinekey textual features. Possible approaches for intermediate representation are Topic Signatures, newlineWord frequency count, Latent Space Approaches using Matrix Factorizations, or Bayesian approaches. These intermediate representations are then used to assign scores for individual newlinelinguistic units within the text and select a subset of linguistic units which maximizes the total newlinescore as the summary of the target text. The mathematical scoring function for the summary newlineis generally composed of components to quantify topical coverage and topical diversity. They newlinereport the accuracy in terms of a measure called the ROUGE score. newlineRelatively less work is available on abstractive multi-document summarization in the past. newlineMost of them utilise sub- syntactical structures which are directly extracted from input documents to generate summary sentences. Sub syntactical structures such as phrases are reorganized to create summary sentences using a method which can ensure relevant topical newlinecoverage, topical diversity and gramaticality. They also incorporate means to ensure factual newlineaccuracy so that sentences generated by the abstract summarization system are factually correct with respect to original corpus. newlineDespite all the attempts to improve summarization in easily quantifiable dimensions