Beyond SumBasic: Task-focused summarization with sentence simplification and lexical expansion

By Lucy Vanderwende, Hisami Suzuki, Chris Brockett, Ani Nenkova. Information Processing & Management, 2007

320 citations recorded by the source corpus.

In recent years, there has been increased interest in topic-focused multi-document summarization. In this task, automatic summaries are produced in response to a specific information request, or topic, stated by the user. The system we have designed to accomplish this task comprises four main components: a generic extractive summarization system, a topic-focusing component, sentence simplification, and lexical expansion of topic words. This paper details each of these components, together with experiments designed to quantify their individual contributions. We include an analysis of our results on two large datasets commonly used to evaluate task-focused summarization, the DUC2005 and DUC2006 datasets, using automatic metrics. Additionally, we include an analysis of our results on the DUC2006 task according to human evaluation metrics. In the human evaluation of system summaries compared to human summaries, i.e., the Pyramid method, our system ranked first out of 22 systems in terms of overall mean Pyramid score; and in the human evaluation of summary responsiveness to the topic, our system ranked third out of 35 systems.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/3827c54958e653b5ce23e19a347f1f52e25592b8

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

Extractive Summarization of Long Documents by Combining Global and Local Context (2019, methodology): “SumBasic (Vanderwende et al., 2007), LSA (Steinberger and Jezek, 2004), and LexRank (Erkan and Radev, 2004) • Neural abstractive summarization models: Attn-Seq2Seq (Nallapati et al.”
A Survey of Text Summarization Techniques (2012, background): “It relies only on word probability to calculate importance [94].”
Distraction-Based Neural Networks for Modeling Document (2016, methodology): “…summarization algorithms, which we listed in the table as Luhn [Luhn, 1958], Edmundson [Edmundson, 1969], LSA [Steinberger and Jezek, 2004], Lex-rank [Erkan and Radev, 2004], Text-rank [Mihalcea and Tarau, 2004], Sumbasic [Vanderwende et al., 2007], and KL-sum [Haghighi and Vanderwende, 2009].”
Exploring Content Models for Multi-Document Summarization (2009, background): “While many variants of the general summarization task have been proposed which utilize such information (Vanderwende et al., 2007; Nastase, 2008), this presupposes that a user knows enough of the content of a document collection in order to propose a query.”
Reinforced Extractive Summarization with Question-Focused Rewards (2018, background): “• SumBasic (Vanderwende et al., 2007) is an ex-tractive approach that assumes words occurring frequently in a document cluster have a higher chance of being included in the summary.”
Problems in Current Text Simplification Research: New Data Can Help (2015, background): “, 1996), summarization (Siddharthan et al., 2004; Klebanov et al., 2004; Vanderwende et al., 2007; Xu and Grishman, 2009), semantic role labeling (Vickrey and Koller, 2008), information extraction (Miwa et al.”
Automatic Caption Generation for News Images (2013, background): “Existing document content representations include simple unigram frequencies (Nenkova and Vanderwende, 2005; Vanderwende et al., 2007; Haghighi and Vanderwende, 2009), syntactic features (such as clause information or dependencies) (Barzilay and McKeown, 2005), and topic representations (Daumé III a”
A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents (2018, methodology): “Examples of prominent approaches include frequency-based methods (Vanderwende et al., 2007), graph-based methods (Erkan and Radev, 2004), topic modeling (Steinberger and Jezek, 2004), and neural models (Nallapati et al., 2017).”
Automatic Text Summarization (2008, background): “Some other researches were about multi-document summarization [7], [8] and summarization for specific domains [9] - [11].”
UvA-DARE (Digital Academic Repository) A Dataset and Evaluation Metrics for Abstractive Compression of Sentences and Short Paragraphs (unknown): “Automated sentence compression condenses a sentence or paragraph to its most important content in order to enhance writing quality, meet document length constraints, and build more accurate document summarization systems (Berg-Kirkpatrick et al., 2011; Vanderwende et al., 2007).”
A New Approach to Improving Multilingual Summarization Using a Genetic Algorithm (2010, unknown): “…1969), key-word - or frequency -based (Luhn, 1958; Edmund-son, 1969; Neto et al., 2000; Steinberger and Jezek, 2004; Kallel et al., 2004; Vanderwende et al., 2007), title -based (Edmundson, 1969; Teufel and Moens, 1997), position -based (Baxendale, 1958; Edmundson, 1969; Lin and Hovy,…”
Dialect Diversity in Text Summarization on Twitter (2020, background): “For topic-focused summarization, Vanderwende et al. [72] score each word by linearly adding its frequency and topic relevance score.”
A Divide-and-Conquer Approach to the Summarization of Long Documents (2020, methodology): “These include simple unsupervised methods [21], [22], graph-based methods that involve”
SemEval-2015 Task 1: Paraphrase and Semantic Similarity in Twitter (PIT) (2015, methodology): “We employ the scoring method used in SumBasic (Nenkova and Vander-wende, 2005; Vanderwende et al., 2007), a simple but powerful summarization system, to ﬁnd salient sentences.”
Recent advances in document summarization (2017, methodology): “For probabilistic approaches [182, 68], sentences are”
Text Summarization Techniques: A Brief Survey (2017, methodology): “[19] proposed the SumBasic system which uses only the word probability approach to determine sentence importance.”