A noisy-channel model for document compression

Daumé, Hal; Marcu, Daniel

doi:10.3115/1073083.1073159

Cited by 47 publications

(31 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Teufel and Moens (1997) and Lin and Hovy (2002) describe representative examples. Recent work in sentence compression (Knight and Marcu 2002;McDonald 2006) and document compression (Daumé III and Marcu 2002) attempts to take small steps beyond sentence extraction. Compression models can be seen as techniques for extracting sentences then dropping extraneous information.…”

Section: Automatic Document Summarizationmentioning

confidence: 99%

Search-based structured prediction

2009

Self Cite

View full text Add to dashboard Cite

We present SEARN, an algorithm for integrating SEARch and lEARNing to solve complex structured prediction problems such as those that occur in natural language, speech, computational biology, and vision. SEARN is a meta-algorithm that transforms these complex problems into simple classification problems to which any binary classifier may be applied. Unlike current algorithms for structured learning that require decomposition of both the loss function and the feature functions over the predicted structure, SEARN is able to learn prediction functions for any loss function and any class of features. Moreover, SEARN comes with a strong, natural theoretical guarantee: good performance on the derived classification problems implies good performance on the structured prediction problem.

show abstract

Section: Automatic Document Summarizationmentioning

confidence: 99%

Search-based structured prediction

2009

Self Cite

View full text Add to dashboard Cite

show abstract

“…This theory guided the annotation of the RST Discourse Treebank (RST-DT) for English, from which several textlevel discourse parsers have been induced (Hernault et al, 2010;Joty et al, 2012;Feng and Hirst, 2014;Li et al, 2014;Ji and Eisenstein, 2014). Such parsers have proven to be useful for various downstream applications (Daumé III and Marcu, 2009;Burstein et al, 2003;Higgins et al, 2004;Thione et al, 2004;Sporleder and Lapata, 2005;Taboada and Mann, 2006;Louis et al, 2010;Bhatia et al, 2015).…”

Section: Introductionmentioning

confidence: 99%

Cross-lingual RST Discourse Parsing

Braud¹,

Coavoux²,

Søgaard³

2017

Proceedings of the 15th Conference of the European Chapter of The Association for Computational Linguistics: Volume 1

View full text Add to dashboard Cite

Discourse parsing is an integral part of understanding information flow and argumentative structure in documents. Most previous research has focused on inducing and evaluating models from the English RST Discourse Treebank. However, discourse treebanks for other languages exist, including Spanish, German, Basque, Dutch and Brazilian Portuguese. The treebanks share the same underlying linguistic theory, but differ slightly in the way documents are annotated. In this paper, we present (a) a new discourse parser which is simpler, yet competitive (significantly better on 2/3 metrics) to state of the art for English, (b) a harmonization of discourse treebanks across languages, enabling us to present (c) what to the best of our knowledge are the first experiments on crosslingual discourse parsing.

show abstract

“…Many studies that have utilized RST have simply adopted EDUs as textual units (Mann and Thompson, 1988;Daumé III and Marcu, 2002;Hirao et al, 2013;Knight and Marcu, 2000). While EDUs are textual units for RST, they are too fine grained as textual units for methods of extractive summarization.…”

Section: Fragmentation Of Informationmentioning

confidence: 99%

“…None of these methods use the discourse structures of documents. Daumé III and Marcu (2002) proposed a noisychannel model that used RST. Although their method generated a well-organized summary, no optimality of information coverage was guaranteed and their method could not accept large texts because of the high computational cost.…”

Section: Related Workmentioning

confidence: 99%

“…It is important for generated summaries to have a discourse structure that is similar to that of the source document. Rhetorical Structure Theory (RST) (Mann and Thompson, 1988) is one way of introducing the discourse structure of a document to a summarization task (Marcu, 1998;Daumé III and Marcu, 2002;Hirao et al, 2013). Hirao et al recently transformed RST trees into dependency trees and used them for single document summarization (Hirao et al, 2013).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Single Document Summarization based on Nested Tree Structure

Kikuchi¹,

Hirao²,

Takamura³

et al. 2014

Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

View full text Add to dashboard Cite

Many methods of text summarization combining sentence selection and sentence compression have recently been proposed. Although the dependency between words has been used in most of these methods, the dependency between sentences, i.e., rhetorical structures, has not been exploited in such joint methods. We used both dependency between words and dependency between sentences by constructing a nested tree, in which nodes in the document tree representing dependency between sentences were replaced by a sentence tree representing dependency between words. We formulated a summarization task as a combinatorial optimization problem, in which the nested tree was trimmed without losing important content in the source document. The results from an empirical evaluation revealed that our method based on the trimming of the nested tree significantly improved the summarization of texts.

show abstract

A noisy-channel model for document compression

Cited by 47 publications

References 12 publications

Search-based structured prediction

Search-based structured prediction

Cross-lingual RST Discourse Parsing

Single Document Summarization based on Nested Tree Structure

Contact Info

Product

Resources

About