Summarization beyond sentence extraction: A probabilistic approach to sentence compression

By Kevin Knight, Daniel Marcu. Artificial Intelligence, 2002

546 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/fa07fa673d8c908e91d22c4566572a72548ccee9

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

Sentence Fusion for Multidocument News Summarization (2005, methodology): “…were based on symbolic reduction rules (Grefenstette 1998; Mani, Gates, and Bloedorn 1999), more recent approaches use an aligned corpus of documents and their human written summaries to determine which constituents can be reduced (Knight and Marcu 2002; Jing and McKeown 2000; Reizler et al. 2003).”
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).”
Multi-document summarization via sentence-level semantic analysis and symmetric matrix factorization (2008, background): “In general, there are two types of summarization: extractive summarization and abstractive summarization [16, 15].”
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).”
FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization (2020, methodology): “This shows that sentence compression (Knight and Marcu, 2002) is the main technique used for this dataset.”
Soft Layer-Specific Multi-Task Summarization with Entailment and Question Generation (2018, unknown): “Automatic text summarization has been progressively improving over the time, initially more focused on extractive and compressive models (Jing and McKeown, 2000; Knight and Marcu, 2002; Clarke and Lapata, 2008; Filippova et al., 2015; Kedzie et al., 2015), and moving more towards compressive and abs”
Soylent: a word processor with a crowd inside (2010, background): “Lazy Turkers in crowdsourced user studies [ 12 ] by adding clearly verifiable, quantitative questions (e.g., “How many sections does the article have?”) that forced the Lazy Turker to read the material being studied.”
HEADS: Headline Generation as Sequence Prediction Using an Abstract Feature-Rich Space (2015, background): “The fact that the local feature function f only depends on the last two assigned categories allows the global optimum of the model to be found by means of a tractable algorithm, whereas otherwise it would be necessary to explore all the |Y| n possible solutions.”
A Noisy-Channel Approach to Question Answering (2003, background): “, 1993), information retrieval (Berger and Lafferty, 1999), and text summarization (Knight and Marcu, 2002), we develop a noisy channel model for QA.”
A Survey of Paraphrasing and Textual Entailment Methods (2009, background): “Sentence compression (Knight & Marcu, 2002; McDonald, 2006; Cohn & Lapata, 2008; Clarke & Lapata, 2008; Cohn & Lapata, 2009; Galanis & Androutsopoulos, 2010), often also a processing stage of text summarization, can be seen as a special case of sentence paraphrasing, as suggested by 3Culicover…”
A Neural Attention Model for Abstractive Sentence Summarization (2015, methodology): “Past work on summarization and compression has used a noisy-channel approach to split and independently estimate a language model and a conditional summarization model (Banko et al., 2000; Knight and Marcu, 2002; Daum´e III and Marcu, 2002 where p ( y ) and p ( x | y ) are estimated separately.”
From Extractive to Abstractive Summarization: A Journey (2019, background): “These are still closer to the extractive techniques, but also perform operations like phrase deletion[35] to shorten the”
Automatic Generation of Story Highlights (2010, background): “It involves creating a short grammatical summary of a single sentence, by removing elements that are considered extraneous, while retaining the most important information (Knight and Marcu, 2002).”
Learning What is Essential in Questions (2017, unknown): “These approaches typically build an internal importance assignment component to assign significance scores to various terms, which is often done using language models, co-occurrence statistics, or their variants (Knight and Marcu, 2002; Hori and Sadaoki, 2004).”
Multi-document summarization using cluster-based link analysis (2008, background): “NewsBlaster) usually needs information fusion [2], sentence compression [10] and reformulation [20].”
Retrieve, Rerank and Rewrite: Soft Template Based Neural Summarization (2018, methodology): “tion include template-based methods (Zhou and Hovy, 2004), syntactic tree pruning (Knight and Marcu, 2002; Clarke and Lapata, 2008) and statistical machine translation techniques (Banko et al.”
BiSET: Bi-directional Selective Encoding with Template for Abstractive Summarization (2019, background): “…in this problem mainly focus on statistical or linguistic-rule-based methods, including those based on extractive and compression (Jing and McKeown, 2000; Knight and Marcu, 2002; Clarke and Lapata, 2010), templates (Zhou and Hovy, 2004) and statistical machine translation (Banko et al., 2000).”
Guiding Extractive Summarization with Question-Answering Rewards (2019, background): “…focus on selecting representative sentences from the document(s) and optionally deleting unimportant sentence constituents to form a summary (Knight and Marcu, 2002; Radev et al., 2004; Zajic et al., 2007; Martins and Smith, 2009; Gillick and Favre, 2009; Lin and Bilmes, 2010; Wang et al.,…”