The Theory and Practice of Discourse Parsing and Summarization

@inproceedings{Marcu2000TheTA,
  title={The Theory and Practice of Discourse Parsing and Summarization},
  author={Daniel Marcu},
  year={2000}
}
  • D. Marcu
  • Published 13 November 2000
  • Sociology
From the Publisher: Until now, most discourse researchers have assumed that full semantic understanding is necessary to derive the discourse structure of texts. This book documents the first serious attempt to construct automatically and use nonsemantic computational structures for text summarization. Daniel Marcu develops a semantics-free theoretical framework that is both general enough to be applicable to naturally occurring texts and concise enough to facilitate an algorithmic approach to… 
View via Publisher
aclweb.org
715 Citations
Highly Influential Citations
89
Background Citations
323
Methods Citations
208
Results Citations
18

715 Citations

Joint Syntacto-Discourse Parsing and the Syntacto-Discourse Treebank

This paper proposes the first end-to-end discourse parser that jointly parses in both syntax and discourse levels, as well as the first syntacto-discourse treebank by integrating the Penn Treebank and the RST Treebank.

Discourse Annotation of Non-native Spontaneous Spoken Responses Using the Rhetorical Structure Theory Framework

A research effort to obtain RST annotations of a large number of non-native spoken responses from a standardized assessment of academic English proficiency found that the highest performing feature resulted in a correlation of 0.612 with scores of discourse coherence provided by expert human raters.

How consistent are our discourse annotations? Insights from mapping RST-DT and PDTB annotations

This article proposes a method for aligning the discourse segments, and evaluates the observed against the expected mappings for explicit and implicit relations separately, finding that while agreement on explicit relations is reasonable, agreement between the frameworks on implicit relations is astonishingly low.

Classification into Rhetorical Functions for AWE Feedback

This work describes the construction of a cascade of two support vector machine classifiers trained on a multi-disciplinary corpus of annotated texts that demonstrates the usefulness of NLP for automated genre analysis and paves the road for future AWE endeavors and forms of automated feedback that could facilitate effective expression of functional meaning in writing.

Discourse classification into rhetorical functions for AWE feedback

The development of the analysis engine for the [TOOL], an AWE program designed to provide genre and discipline-specific feedback on the functional units of research article discourse, is reported on.

HILDA: A Discourse Parser Using Support Vector Machine Classification

This article presents HILDA, an implemented discourse parser based on RST and Support Vector Machine (SVM) classification that outperforms other discourse parsers for tree structure construction and discourse relation labeling.

An effective Discourse Parser that uses Rich Linguistic Information

The modified shift-reduce parsing model that uses the authors' relation classifier significantly outperforms a right-branching majority-class baseline and a statistically significant improvement in classifying relations over attribute-value learning paradigms such as Decision Trees, RIPPER and Naive Bayes.

Improving the efficiency and capabilities of document structuring

This thesis deals with document structure, a recent theory which describes those aspects of a document’s layout which affect its meaning, a useful intermediate representation in the process of NLG.

Simple Signals for Complex Rhetorics: On Rhetorical Analysis with Rich-Feature Support Vector Models

A machinelearning governed approach to such an analysis in the framework of Rhetorical Structure Theory is presented, which defines a chain of annotation tools that profits from a new underspecified representation of rhetorical structure.

Towards Automatic Classification of Discourse Elements in Essays

Using a relatively small corpus of manually annotated data, this work uses Bayesian classification to identify thesis statements and yields results that are much closer to human performance than the results produced by two baseline systems.
...

References

SHOWING 1-6 OF 6 REFERENCES

Rhetorical Structure Theory: Toward a functional theory of text organization

This paper establishes a new definitional foundation for RST and examines three Claims of RST: the predominance of nucleus/satellite structural pattems, the functional basis of hierarchy, and the communicative role oftext Structure.

Directory of Graduate Programs in Computational Linguistics

This Directory is being sent to all A C L members and additional copies, or non-subscript ion copies, are available for $5 per copy f rom.

journals-orders@mit.edu. Institutional orders for back issues (1988-) should also be ordered from MIT Press Journals

  • 1988

Niagara-on-the-Lake 1999 College Park 1999 College Park 1999 College Park

  • 1999

CREDIT CARDS: Payments must be made to the ACL Office in the USA. Visa and Mastercard only. Email, fax or hardcopy are acceptable

  • CREDIT CARDS: Payments must be made to the ACL Office in the USA. Visa and Mastercard only. Email, fax or hardcopy are acceptable

Las Cruces 1994 Las Cruces 1995 Cambridge

  • 1996