Sentence Fusion for Multidocument News Summarization

By Regina Barzilay, K. McKeown. International Conference on Computational Logic, 2005

475 citations recorded by the source corpus.

A system that can produce informative summaries, highlighting common information found in many online documents, will help Web users to pinpoint information that they need without extensive reading. In this article, we introduce sentence fusion, a novel text-to-text generation technique for synthesizing common information across documents. Sentence fusion involves bottom-up local multisequence alignment to identify phrases conveying similar information and statistical generation to combine common phrases into a sentence. Sentence fusion moves the summarization field from the use of purely extractive methods to the generation of abstracts that contain sentences not found in any of the input documents and can synthesize information across sources.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/21a7b165b2e09cfc166bbbc69fef0732d6d99d5c

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

NLG Challenge : Neural Models vs . Templates (2018, background): “The latter can be a syntactic tree (Mani et al., 1999; Barzilay and McKeown, 2005), a set of abstract logic forms (Phillips, 1993), key-value attribute pairs (Chisholm et al.”
Abstractive Cross-Language Summarization via Translation Model Enhanced Predicate Argument Structure Fusing (2016, unknown): “monolingual document summarization [4]–[7].”
Dynamic Planning in Open-Ended Dialogue using Reinforcement Learning (2022, background): “” Sentence fusion combines the selected utterances into a single cohesive response [2, 10, 25], such as “On average, male lions weigh 420 lbs and are 3.”
TreeTalk: Composition and Compression of Trees for Image Descriptions (2014, background): “Sentence Fusion Sentence fusion has been studied mostly for multi-document summarization (Barzilay and McKeown, 2005), where redundancy across multiple sentences serves as a guideline for syntactic and semantic validity of generation.”
AgreeSum: Agreement-Oriented Multi-Document Summarization (2021, background): “mation “centroids” among multiple related documents, so as to allow internet users to more efficiently understand events (Radev et al., 2000; Barzilay and McKeown, 2005).”
Multi-Sentence Compression: Finding Shortest Paths in Word Graphs (2010, background): “Input sentences are parsed into trees, from those trees a new dependency structure is generated, and this structure is ﬁnally converted into a sentence (Barzilay & McKeown, 2005; Filippova & Strube, 2008b; Wan et al., 2009).”
Automatic Caption Generation for News Images (2013, background): “Other approaches include sentence compression which helps make the summary more concentrate on the gist hence avoid redundancies (Knight and Marcu, 2002; Clarke, 2008), and sentence fusion which provides a flexible framework for both single- and multi- document summarization by taking syntactic info”
Controlling the Amount of Verbatim Copying in Abstractive Summarization (2019, unknown): “Abstractive summarization distills the source text into its essential meanings, then performs language generation from the representation to produce an abstract (Barzilay and McKeown 2005; Liu et al. 2015; Liao, Lebanoff, and Liu 2018; Hardy and Vlachos 2018).”
Discriminative Syntax-Based Word Ordering for Text Generation (2015, unknown): “Applications that can beneﬁt from better text generation algorithms include machine translation (Koehn 2010), abstractive text summarization (Barzilay and McKeown 2005), and grammar correction (Lee and Seneff 2006).”
Recent advances in document summarization (2017, unknown): “More sophisticated operations may also be used to enhance compactness and informativeness, such as paraphrasing and sentence fusion [9].”
Understanding Points of Correspondence between Sentences for Abstractive Summarization (2020, background): “Early attempts to fuse sentences build a dependency graph from sentences, then decode a tree from the graph using integer linear programming, finally linearize the tree to generate a summary sentence (Barzilay and McKeown, 2005; Filippova and Strube, 2008; Thadani and McKeown, 2013a).”
Template Guided Text Generation for Task Oriented Dialogue (2020, methodology): “Our template based approach bears similarities to sentence fusion (Barzilay and McKeown, 2005), and prototype based text editing (Hossain et al., 2020; Cao et al., 2018; Guu et al., 2018; Wu et al., 2019).”
A Survey of Paraphrasing and Textual Entailment Methods (2009, background): “During that stage, especially when generating a single summary from several documents (Barzilay & McKeown, 2005), it is important to avoid selecting sentences (e.g., from different news articles about the same event) that convey the same information (paraphrases) as other sentences that have…”
Benchmarking Large Language Models for News Summarization (2023, background): “Summarization evaluation is another active area of research.”
A compositional context sensitive multi-document summarizer: exploring the factors that influence summarization (2006, background): “go beyond sentence extraction, reformulating or simplifying the text of the original articles, must decide which sentences should be simplified, compressed, fused together or rewritten [10, 11, 28, 2, 6].”
Generating Phrasal and Sentential Paraphrases: A Survey of Data-Driven Methods (2010, background): “On this note, Barzilay and McKeown (2005) exploit the redundancy present in a given set of sentences by detecting paraphrastic parts and fusing them into a single coherent sentence.”