Inferring Strategies for Sentence Ordering in Multidocument News Summarization

By Regina Barzilay, Noémie Elhadad, K. McKeown. Journal of Artificial Intelligence Research, 2002

378 citations recorded by the source corpus.

The problem of organizing information for multidocument summarization so that the generated summary is coherent has received relatively little attention. While sentence ordering for single document summarization can be determined from the ordering of sentences in the input article, this is not the case for multidocument summarization where summary sentences may be drawn from different input articles. In this paper, we propose a methodology for studying the properties of ordering information in the news genre and describe experiments done on a corpus of multiple acceptable orderings we developed for the task. Based on these experiments, we implemented a strategy for ordering information that combines constraints from chronological order of events and topical relatedness. Evaluation of our augmented algorithm shows a significant improvement of the ordering over two baseline strategies.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/b0330630a66b982d243d8b5efcd1beb36714cdff

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

A Study of Global Inference Algorithms in Multi-document Summarization (2007, background): “This formulation also does not specify any ordering preferences on the textual units extracted for the summary [2].”
Automatic Text Summarization: Past, Present and Future (2013, methodology): “For example, a clustering algorithm can be used to identify topics in the set of input documents and discover in what order the topics are presented in the input documents [3], this in turn could be used to present sentences in an order similar to that observed in the input set.”
Recent advances in document summarization (2017, methodology): “Classic reordering approaches include inferring order from weighted sentence graph [36], or perform a chronological ordering algorithm [8] that sorts sentences based on timestamp and position.”
VerbOcean: Mining the Web for Fine-Grained Semantic Verb Relations (2004, background): “another is also useful to determine the order of the events (Barzilay et al. 2002).”
Probabilistic Text Structuring: Experiments with Sentence Ordering (2003, methodology): “Barzilay et al. (2002) collected ten sets of articles each consisting of two to three articles reporting the same event and simulated M ULTI G EN by manually selecting the sentences to be included in the ﬁnal summary.”
Overview of the TAC 2010 Knowledge Base Population Track (2010, methodology): “, 2005), Multi-document Text summarization (Elhadad et al., 2002) and Template Based Question Answering (Schockaert et al.”
Sentence Fusion for Multidocument News Summarization (2005, background): “In fact, previous applications of multisequence alignment have been shown to increase the accuracy of the comparison in other NLP tasks (Barzilay and Lee 2002; Bangalore, Murdock, and Riccardi 2002; Lacatusu, Maiorano, and Harabagiu 2004); unlike our work these approaches operate on strings, not…”
Individual and Domain Adaptation in Sentence Planning for Dialogue (2007, methodology): “The approach of learning a ranking from user feedback has been applied to multimedia presentation planning (Stent & Guo, 2005) and to the joint optimization of the syntactic realizer and the text-to-speech engine (Nakatsu & White, 2006).”
Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation (2017, methodology): “Barzilay and Lapata (2006) present a system that learns how to aggregate on the basis of a parellel corpus of sentences and corresponding database entries, by looking for similarities between entries. As was the case with the content selection method of Barzilay and Lapata (2005), Barzilay and Lapat”
Query based event extraction along a timeline (2004, background): “For multidocument summarization (MDS), the ordering of sentences within a summary has also been explored to produce coherent summaries for the reader[3][4].”
A Bottom-Up Approach to Sentence Ordering for Multi-Document Summarization (2006, methodology): “Existing methods for sentence ordering are divided into two approaches: making use of chronological information (McKeown et al., 1999; Lin and Hovy, 2001; Barzilay et al., 2002; Okazaki et al., 2004), and learning the natural order of sentences from large corpora (Lapata, 2003; Barzilay and Lee, 200”
TIARA: A Tool for Annotating Discourse Relations and Sentence Reordering (2020, background): “There are however some studies that explain how to order sentences to generate coherent texts in NLP applications, (Barzilay et al., 2002; Okazaki et al., 2004; Li and Jurafsky, 2017; Xu et al., 2019).”
Sentence Ordering using Recurrent Neural Networks (2016, neutral): “Barzilay and Elhadad (2002) discuss the importance of an explicit ordering component in MDS systems.”