Extractive summarisation via sentence removal

Abstract

Many on-line services allow users to describe their opinions about a product or a service through a review. In order to help other users to find out the major opinion about a given topic, without the effort to read several reviews, multi-document summarisation is required. This research proposes an approach for extractive summarisation, supporting different scoring techniques, such as cosine similarity or divergence, as a method for finding representative sentences. The main contribution of this paper is the definition of an algorithm for sentence removal, developed to maximise the score between the summary and the original document. Instead of ranking the sentences and selecting the most important ones, the algorithm iteratively removes unimportant sentences until a desired compression rate is reached. Experimental results show that variations of the sentence removal algorithm provide good performance.

A Probabilistic Approach for Extractive Summarization Based on Clustering Cum Graph Ranking Method

“…[37] propose a hierarchical selective encoding network for both sentence-level and document-level representations and data containing important information is extracted. The method introduced in [38] improves upon the cohesiveness of the summaries generated by the extractive summarization systems. It is based on a post-processing step that binds dangling co-reference to the most important entity in a given co-reference chain.…”

Not All Reviews Are Equal: Towards Addressing Reviewer Biases for Opinion Summarization

“…An opinion summary can be presented in different ways, catering to the different needs of readers. The summary can be on one product (Angelidis and Lapata, 2018;Hu and Liu, 2004a), comparing two products (Sipos and Joachims, 2013) or generate a summary in response to a query (Bonzanini et al, 2013).…”

Finding and enumerating large intersections

“…An extractive summary of a large collection of sentences, e.g., from news, comments or product reviews, is a small subset of sentences that reflects the most relevant content. Various summarization methods are based on scores, sentence similarity measures, and partly also graphtheoretic concepts, see, for instance, [4,10,15,16,18]. In our own approach 2 we consider sentences, after some preprocessing, as sets of words.…”