Sentence Reduction for Automatic Text Summarization

By Hongyan Jing. 2000

324 citations recorded by the source corpus.

We present a novel sentence reduction system for automatically removing extraneous phrases from sentences that are extracted from a document for summarization purpose. The system uses multiple sources of knowledge to decide which phrases in an extracted sentence can be removed, including syntactic knowledge, context information, and statistics computed from a corpus which consists of examples written by human professionals. Reduction can significantly improve the conciseness of automatic summaries.

Subfields: Artificial Intelligence, Natural Language Processing

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

In Natural Language Processing

Citations in the corpus

Get To The Point: Summarization with Pointer-Generator Networks (2017, methodology): “Prior to modern neural methods, abstractive summarization received less attention than extractive summarization, but Jing (2000) explored cutting unimportant parts of sentences to create summaries, and Cheung and Penn (2014) explore sentence fusion using dependency trees.”
Multi-Reward Reinforced Summarization with Saliency and Entailment (2018, methodology): “…the task of generating a natural short summary of a long document, is more challenging than the extractive paradigm, which only involves selection of important sentences or grammatical sub-sentences (Jing, 2000; Knight and Marcu, 2002; Clarke and La-pata, 2008; Filippova et al., 2015).”
Sentence Compression by Deletion with LSTMs (2015, methodology): “That is, one usually drops constituents or prunes dependency edges (Jing, 2000; Knight & Marcu, 2000; McDonald, 2006; Clarke & Lapata, 2008; Berg-Kirkpatrick et al., 2011; Filippova & Altun, 2013).”
Sentence Compression Beyond Word Deletion (2008, background): “Examples include the generation of subtitles from spoken transcripts (Vandeghinste and Pan, 2004), the display of text on small screens such as mobile phones or PDAs (Corston-Oliver, 2001), and, notably, summarisation (Jing, 2000; Lin, 2003).”
Title Generation with Quasi-Synchronous Grammar (2010, background): “An alternative abstractive or “bottom-up” approach involves identifying high-interest words and phrases in the source text, and combining them into new sentences guided by a language model (Banko et al., 2000; Soricut and Marcu, 2007).”
Discourse Constraints for Document Compression (2010, unknown): “Unlike Jing (2000) we explicitly identify topically important words and assume speciﬁc representations of discourse structure.”
Constraint-Based Sentence Compression: An Integer Programming Approach (2006, methodology): “In contrast to Jing (2000), the bulk of the research on sentence compression relies exclusively on corpus data for modelling the compression process without recourse to extensive knowledge sources (e.g., WordNet).”
Towards Improving Abstractive Summarization via Entailment Generation (2017, background): “, selecting which sentences to keep vs discard, and also compressing based on choosing grammatically correct sub-sentences having the most important pieces of information (Jing, 2000; Knight and Marcu, 2002; Clarke and Lapata, 2008; Filippova et al., 2015).”
Benchmarking Large Language Models for News Summarization (2023, background): “Many automatic metrics have been proposed (Lin, 2004; Zhang* et al., 2020; Sellam et al., 2020; Durmus et al., 2020; Maynez et al., 2020; Deutsch and Roth, 2021) but they do not always correlate with human evaluation of summarization systems (Fab-bri et al., 2020; Durmus et al., 2022).”
Improving Natural Language Processing Tasks with Human Gaze-Guided Neural Attention (2020, methodology): “Sentence compression As a second task, we opted for deletion-based sentence compression that aims to delete unimportant words from an input sentence [31, 38, 47, 12, 20].”
Global inference for sentence compression : an integer linear programming approach (2008, methodology): “In contrast to Jing (2000), the bulk of the research on sentence compression relies exclusively on corpus data for modeling the compression process without recourse to extensive knowledge sources (e.g., WordNet).”
Unsupervised Sentence Compression using Denoising Auto-Encoders (2018, methodology): “Within text summarization, two broad approaches exist: extractive approaches extract explicit tokens or phrases from the reference text, whereas abstrac-tive approaches involve a compressed paraphrasing of the reference text, similar to the approach humans might take (Jing, 2000, 2002).”
Automatic Generation of Story Highlights (2010, background): “Interfacing extractive summarization with a sentence compression module could improve the conciseness of the generated summaries and render them more informative (Jing, 2000; Lin, 2003; Zajic et al., 2007).”
UvA-DARE (Digital Academic Repository) A Dataset and Evaluation Metrics for Abstractive Compression of Sentences and Short Paragraphs (unknown): “Automatic metrics: Early automatic metrics for evaluation of compressions include success rate (Jing, 2000), defined as accuracy of individual word or constituent deletion decisions; Simple String Accuracy (string edit distance), introduced by Banga-”