Headline Generation Based on Statistical Translation

By Michele Banko, Vibhu Mittal, Michael J. Witbrock. 2000

277 citations recorded by the source corpus.

Extractive summarization techniques cannot generate document summaries shorter than a single sentence, something that is often required. An ideal summarization system would understand each document and generate an appropriate summary directly from the results of that understanding. A more practical approach to this problem results in the use of an approximation: viewing summarization as a problem analogous to statistical machine translation. The issue then becomes one of generating a target document in a more concise language from a source document in a more verbose language. This paper presents results on experiments using this approach, in which statistical models of the term selection and term ordering are jointly applied to produce summaries in a style learned from a training corpus.

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

Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond (2016, background): “…of the other notable work in the task of abstractive summarization includes us-ing traditional phrase-table based machine translation approaches (Banko et al., 2000), compression using weighted tree-transformation rules (Cohn and Lapata, 2008) and quasi-synchronous grammar approaches (Woodsend…”
Neural Summarization by Extracting Sentences and Words (2016, methodology): “The idea of creating a summary by extracting words from the source document was pioneered in Banko et al. (2000) who view summarization as a problem analogous to statistical machine translation and generate headlines using statistical models for selecting and ordering the summary words.”
Controlling Output Length in Neural Encoder-Decoders (2016, background): “There are also several studies of abstractive sentence summarization us-ing syntactic transduction (Cohn and Lapata, 2008; Napoles et al., 2011) or taking a phrase-based statistical machine translation approach (Banko et al., 2000; Wubben et al., 2012; Cohn and Lapata, 2013).”
Hedge Trimmer: A Parse-and-Trim Approach to Headline Generation (2003, neutral): “This approach has been explored in (Zajic et al., 2002) and (Banko et al., 2000).”
Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting (2018, neutral): “The latter abstractive approach involves rewriting the summary (Banko et al., 2000; Zajic et al., 2004), and has seen substantial recent gains due to neural sequence-to-sequence models (Chopra et al., 2016; Nallap-ati et al., 2016; See et al., 2017; Paulus et al., 2018).”
Retrieve, Rerank and Rewrite: Soft Template Based Neural Summarization (2018, methodology): “Early studies on sentence summariza- 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., 2000).”
Faithful to the Original: Fact Aware Neural Abstractive Summarization (2017, methodology): “Early studies for sentence summarization included rule-based methods (Zajic et al. 2007), syntactic tree pruning (Knight and Marcu 2002) and statistical machine translation techniques (Banko, Mittal, and Witbrock 2000).”
Neural Headline Generation with Minimum Risk Training (2016, background): “For example, [2] applies statistical models for content selection and surface realization to produce headlines.”
Abstract Text Summarization with a Convolutional Seq2seq Model (2019, methodology): “Reference [17] used a conventional phrase-table based machine translation model to realize text summarization.”
Automatic Generation of Story Highlights (2010, background): “Our approach bears some resemblance to headline generation (Dorr et al., 2003; Banko et al., 2000), although we output several sentences rather than a single one.”
From Extractive to Abstractive Summarization: A Journey (2019, methodology): “[3] proposed using statistical machine translation for generating”
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).”
How Many Words Is a Picture Worth? Automatic Caption Generation for News Images (2010, methodology): “Banko et al. (2000) propose a bag-of-words model for headline generation.”
Zero-Shot Cross-Lingual Abstractive Sentence Summarization through Teaching Generation and Attention (2019, methodology): “There are various methods exploring the effective way to model the monolingual ASSUM process including statistical models (Banko et al., 2000; Cohn and Lapata, 2008) or neural models (Rush et al., 2015; Chopra et al., 2016; Nallapati et al., 2016).”
HEADS: Headline Generation as Sequence Prediction Using an Abstract Feature-Rich Space (2015, methodology): “This follows from the observation that good headlines must contain about eight tokens (Banko et al., 2000).”
Language modelling ’ s generative model : is it rational ? (2004, background): “…plausible, presents problems on deeper analysis; and the analogous account is even less plausible and more questionable for other tasks, though they have been presented as other applications of a generic ‘translation model’ for text pairs (as in Berger and Lafferty 1999, Banko et al. 2000).”
Global Encoding for Abstractive Summarization (2018, methodology): “Researchers developed many statistical methods and linguistic-rule-based methods to study automatic summarization (Banko et al., 2000; Dorr et al., 2003; Zajic et al., 2004; Cohn and Lapata, 2008). With the development of Neural Network in NLP, more and more researches have appeared in abstractive s”