Statistics-Based Summarization - Step One: Sentence Compression

By Kevin Knight, Daniel Marcu. AAAI/IAAI, 2000

501 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/25f51f4132626a645924b3c8b3edcbdcc35c48a3

How researchers see this paper

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

Citations in the corpus

Hedge Trimmer: A Parse-and-Trim Approach to Headline Generation (2003, background): “We focus instead on the construction of headline-style abstracts from a single story.”
Annotating and Modeling Fine-grained Factuality in Summarization (2021, background): “Earlier work on abstraction (Barzilay et al., 1999; Carenini and Cheung, 2008) and compression (Knight and Marcu, 2000; Berg-Kirkpatrick et al., 2011; Woodsend and Lapata, 2012; Durrett et al., 2016) in summarization has typically focused evaluation on content selection and grammaticality, with…”
Introduction to the Special Issue on Summarization (2002, methodology): “In an attempt to learn rules for reduction, Knight and Marcu (2000) use expectation maximization to train a system to compress the syntactic parse tree of a sentence in order to produce a shorter but still maximally grammatical version.”
TreeTalk: Composition and Compression of Trees for Image Descriptions (2014, background): “Much work has considered deletion-only edits like ours (Knight and Marcu, 2000; Turner and Charniak, 2005; Cohn and Lapata, 2007; Filippova and Altun, 2013), while recent ones explore more complex edits, such as substitutions, insertions and reordering (Cohn and Lapata, 2008).”
SUMMAC: a text summarization evaluation (2002, background): “…approaches have become quite dominant, including the machine learning of feature combinations (Kupiec, Pedersen and Chen 1995; Mani and Bloedorn 1998; Aone, Okurowski, Gorlinsky and Larsen 1999; Teufel and Moens 1999), as well as the learning of sentence-shortening rules (Knight and Marcu 2000).”
Robust Training under Linguistic Adversity (2017, unknown): “The second approach to syntactic noise is based on sentence compression (“C OMP ”: Knight and Marcu (2000)), which aims to “trim” an input of peripheral content, while maintaining grammati-cality, and also the syntax of the original as much as possible.”
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 Simplification by Monolingual Machine Translation (2012, background): “Sentence simplification can also serve to preprocess the input of other tasks, such as summarization (Knight and Marcu, 2000), parsing, machine translation (Chandrasekar et al.”
Overcoming the Lack of Parallel Data in Sentence Compression (2013, background): “For example, Knight & Marcu (2000) only induce non-lexicalized CFG rules, many of which occurred only once in the training data.”
A Survey on Automatic Text Summarization (2007, unknown): “In (Knight and Marcu, 2000), the source and channel models are simple models inspired by probabilistic context-free grammars (PCFGs).”
Jointly Learning to Extract and Compress (2011, background): “While pure extraction is certainly simple and does guarantee some minimal readability, Lin (2003) showed that sentence compression (Knight and Marcu, 2001; McDonald, 2006; Clarke and Lap-ata, 2008) has the potential to improve the resulting summaries.”
LexRank: Graph-based Centrality as Salience in Text Summarization (2004, methodology): “Centroid-based summarization has given promising results in the past, and it has resulted in the first web-based multi-document summarization system1 (Radev, Blair-Goldensohn, & Zhang, 2001).”
Headline Generation Based on Statistical Translation (2000, background): “As in any language generation task, summarization can be conceptually modeled as consisting of two major sub-tasks: (1) content selection, and (2) surface realization.”
Universal Conceptual Cognitive Annotation (UCCA) (2013, background): “, 2004), summarization (Knight and Marcu, 2000), and question answering (Wang et al.”
A Scalable Global Model for Summarization (2009, methodology): “In particular, we are interested in creating compressed alternatives for the original sentence by manipulating its parse tree (Knight and Marcu, 2000).”
Query based event extraction along a timeline (2004, background): “Kevin and Marcu[9] explored summarization by sentence compression.”
Syntactic Simplification and Text Cohesion (2006, background): “Since then, Knight and Marcu (2000) and Riezler et al.”