Single Document Summarization based on Nested Tree Structure

Abstract

Many methods of text summarization combining sentence selection and sentence compression have recently been proposed. Although the dependency between words has been used in most of these methods, the dependency between sentences, i.e., rhetorical structures, has not been exploited in such joint methods. We used both dependency between words and dependency between sentences by constructing a nested tree, in which nodes in the document tree representing dependency between sentences were replaced by a sentence tree representing dependency between words. We formulated a summarization task as a combinatorial optimization problem, in which the nested tree was trimmed without losing important content in the source document. The results from an empirical evaluation revealed that our method based on the trimming of the nested tree significantly improved the summarization of texts.

Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting

“…Earlier attempts in this paradigm used Hidden Markov Models and rule-based systems (Jing and McKeown, 2000), statistical models based on parse trees (Knight and Marcu, 2000), and integer linear programming based methods (Martins and Smith, 2009;Gillick and Favre, 2009;Clarke and Lapata, 2010;Berg-Kirkpatrick et al, 2011). Recent approaches investigated discourse structures (Louis et al, 2010;Hirao et al, 2013;Kikuchi et al, 2014;Wang et al, 2015), graph cuts (Qian and Liu, 2013), and parse trees (Li et al, 2014;Bing et al, 2015). For neural models, Cheng and Lapata (2016) used a second neural net to select words from an extractor's output.…”

The Role of Discourse Units in Near-Extractive Summarization

“…The more central units to each RST relation are nuclei while the more peripheral are satellites. Prior work in document compression (Daumé and Marcu, 2002) and single-document summarization (Marcu, 1999;Louis et al, 2010;Hirao et al, 2013;Kikuchi et al, 2014;Yoshida et al, 2014) has shown that the structure of discourse trees, especially the nuclearity of non-terminal discourse relations in the tree, is valuable for content selection in summarization. The Penn Discourse Treebank (PDTB) (Prasad et al, 2008) on the other hand is theory-neutral and does not define a recursive structure for the entire document like RST.…”

“…Finer-grained units such as n-grams are frequently used for quantifying content salience and redundancy prior to summarization over sentences (Filatova and Hatzivassiloglou, 2004;Thadani and McKeown, 2008;Gillick and Favre, 2009;Lin and Bilmes, 2011;Cao et al, 2015). In contrast, when the task at hand is more abstractive, the units are more finegrained, e.g., n-grams and phrases in abstractive summarization (Kikuchi et al, 2014;Liu et al, 2015;Bing et al, 2015), n-grams and humanannotated concept units in summarization evaluation (Lin, 2004;Hovy et al, 2006). Recently, subject-verb-object triplets were used to automatically identify concept units (Yang et al, 2016) and in abstractive summarization (Li, 2015); however, this requires semantic processing while EDU segmentation is presently more accurate and scalable.…”

Summarizing a Document by Trimming the Discourse Tree

“…When we need to generate a summary with high compression rate (small L max ), it is difficult to produce informative summaries by simply extracting predefined textual units such as EDUs or sentences. Recently, Kikuchi et al [37] proposed a discourse-based summarization method that integrates sentence extraction and compression. They build a nested dependency tree that represents the dependency relationships between sentences and words and then obtain a summary by trimming the tree.…”