Rhetorical Structure Theory: Toward a functional theory of text organization

By W. Mann, Sandra A. Thompson. 1988

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Towards Coherent and Cohesive Long-form Text Generation (2018, background): “, 1998), resulted in many different formalisms, such as Rhetorical Structure Theory (Mann and Thompson, 1988), and other forms of coherence and cohesion relations and their quantification (Mani et al.”
Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems (2015, background): “To minimise handcrafting, Stent and Molina (2009) proposed learning sentence planning rules directly from a corpus of utterances labelled with Rhetorical Structure Theory (RST) discourse relations (Mann and Thompson, 1988).”
Ranking Sentences for Extractive Summarization with Reinforcement Learning (2018, background): “In the future we would like to focus on smaller discourse units (Mann and Thompson, 1988) rather than individual sentences, modeling compression and extraction jointly.”
Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation (2017, methodology): “In a similar vein, both Hovy (1991) and Moore and Paris (1993) interpreted the relations of Rhetorical Structure Theory (Mann & Thompson, 1988) as operators for text planning.”
Learning Answer-Entailing Structures for Machine Comprehension (2015, methodology): “The sentences with discourse relations are related to each other by means of substitution, ellipsis, conjunction and lexical cohesion, etc (Mann and Thompson, 1988) and can help us answer certain kinds of questions (Jansen et al., 2014).”
Justifying Recommendations using Distantly-Labeled Reviews and Fine-Grained Aspects (2019, background): “Instead of a complete sentence or phrase, we define each segment as an Elementary Discourse Unit (EDU; (Mann and Thompson, 1988)) which corresponds to a sequence of clauses.”
A Survey of Cross-lingual Word Embedding Models (2017, neutral): “…is usually done according to Rhetorical Structure 15. https://github.com/jiangfeng1124/acl15-clnndep 16. http://www.cnts.ua.ac.be/conll2003/ner/ 17. http://web.eecs.umich.edu/mihalcea/downloads.html#semcor 18. https://github.com/coastalcph/noda2015_sst Theory (RST) (Mann & Thompson, 1988).”
Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics (2021, background): “RST is an elaborate system for annotating coherence relations in discourse.”
Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialogue (2019, background): “In order to overcome these challenges, we propose the use of structured meaning representations like those explored widely in (hybrid) rule-based NLG systems (Rambow et al., 2001; Reiter and Dale, 2000; Walker et al., 2007).”
Science Question Answering using Instructional Materials (2016, methodology): “Finally, we also have features corresponding to the RST (Mann and Thompson, 1988) and coreference links to enable inference across sentences.”