Figure 5 - available via license: Creative Commons Attribution 3.0 Unported
Content may be subject to copyright.
Schematic diagram of RST tree construction process (a) shows a top-down parsing algorithm; (b) shows an example which uses (a) to build a subtree of the RST tree corresponding to Figure 2
Source publication
This paper proposes a two-stage automatic text summarization method based on discourse structure, aiming to improve the accuracy and coherence of the summary. In the extractive stage, a text encoder divides the long text into elementary discourse units (EDUs). Then a parse tree based on rhetorical structure theory is constructed for the whole disco...
Contexts in source publication
Context 1
... the terminal nodes of the paragraph tree were replaced with a sentence tree, and the terminal nodes of the sentence tree were replaced with an EDU tree. The construction process of the RST tree is shown in Figure 5. At this point, the RST discourse tree corresponding to the entire text D was constructed, and terminal nodes (EDUs) marked as the nucleus set the extraction depth according to the summary length requirement. ...
Context 2
... extraction, the EDU sequence of text D was further reduced to obtain D'={E 1 ', E 2 ', ..., E l '} (l represents the number of extracted EDUs, l<L), which was used as input for the generation stage. Taking the RST tree in Figure 5 as an example, if the minimum depth is 3 and the extraction depth is set to 5, the extracted values are E1 and E8. ...
Similar publications
![RST fragment from RST-DT: Satellites point to nuclei (e.g., [28] is a...](publication/384188786/figure/fig2/AS:11431281319354617@1742582843846/RST-fragment-from-RST-DT-Satellites-point-to-nuclei-eg-28-is-a-consequence-of_Q320.jpg)
In this article we present Enhanced Rhetorical Structure Theory (eRST), a new theoretical framework for computational discourse analysis, based on an expansion of Rhetorical Structure Theory (RST). The framework encompasses discourse relation graphs with tree-breaking, non-projective and concurrent relations, as well as implicit and explicit signal...
We introduce the first version of the Czech RST Discourse Treebank, a collection of Czech journalistic texts manually annotated using the Rhetorical Structure Theory (RST).
Existing cross-document event coreference resolution models, which either compute mention similarity directly or enhance mention representation by extracting event arguments (such as location, time, agent, and patient), lacking the ability to utilize document-level information. As a result, they struggle to capture long-distance dependencies. This...
