Rhetorical Structure Theory

Rhetorical Structure Theory (RST) is a theory of text structure that is being extended to serve as a theoretical basis for computational text planning. Text structures in RST are hierarchic, built on small patterns called schemas. The schemas which compose the structural hierarchy of a text describe the functions of the parts rather than their form characteristics. Relations between text parts, comparable to conjunctive relations, are a prominent part of RST’s definitional machinery. Recent work has put RST onto a new definitional basis. This paper details the current status of descriptive RST, along with efforts to create a constructive version for use as a basis for programming a text planner.

Interactional coherence in asynchronous learning networks: A rhetorical approach

Leichte Sprache (LS; easy-to-read German) defines a variety of German characterized by simplified syntactic constructions and a small vocabulary. It provides barrier-free information for a wide spectrum of people with cognitive impairments, learning difficulties, and/or a low level of literacy in the German language. The levels of difficulty of a range of syntactic constructions were systematically evaluated with LS readers as part of the recent LeiSA project (Bock, 2019). That study identified a number of constructions that were evaluated as being easy to comprehend but which fell beyond the definition of LS. We therefore want to broaden the scope of LS to include further constructions that LS readers can easily manage and that they might find useful for putting their thoughts into words. For constructions not considered in the LeiSA study, we performed a comparative treebank study of constructions attested to in a collection of 245 LS documents from a variety of sources. Employing the treebanks TüBa-D/S (also called VERBMOBIL) and TüBa-D/Z, we compared the frequency of such constructions in those texts with their incidence in spoken and written German sources produced without the explicit goal of facilitating comprehensibility. The resulting extension is called Extended Leichte Sprache (ELS). To date, text in LS has generally been produced by authors proficient in standard German. In order to enable text production by LS readers themselves, we developed a computational linguistic system, dubbed ExtendedEasyTalk. This system supports LS readers in formulating grammatically correct and semantically coherent texts covering constructions in ELS. This paper outlines the principal components: (1) a natural-language paraphrase generator that supports fast and correct text production while taking readership-design aspects into account, and (2) explicit coherence specifications based on Rhetorical Structure Theory (RST) to express the communicative function of sentences. The system’s writing-workshop mode controls the options in (1) and (2). Mandatory questions generated by the system aim to teach the user when and how to consider audience-design concepts. Accordingly, users are trained in text production in a similar way to elementary school students, who also tend to omit audience-design cues. Importantly, we illustrate in this paper how to make the dialogues of these components intuitive and easy to use to avoid overtaxing the user. We also report the results of our evaluation of the software with different user groups.

This paper discusses the planning of multisentential text by computer. In order to construct coherent paragraphs, we have been using relations from Rhetorical Structure Theory (RST) operationalized as plans. The paper first describes, in some detail, the current method of planning a paragraph using operationalized RST relation/plans. It then makes two points that illustrate why RST relation/plans are an ideal tool for planning paragraphs. First, these relation/plans can be shown to combine the best features of paragraph-sized schemas and clause-sized planning rules under a top-down planning regime in a way which affords much flexibility to the user. Second, RST relation/plans can support both standard top-down planning and open-ended conversation-like behavior; a small difference in treatment gives rise to either paradigm.

Based on a corpus of Austrian students’ texts from three disciplines (personnel management, business psychology, economic history) analysed with Rhetorical Structure Theory (RST), this paper investigates the macro-structural expectations which tables of content (ToCs) raise, the cues by which these expectations are triggered, and the “predictive quality” of ToCs. The ToCs in the personnel management group’s texts offer the best “prediction” of the actual macrostructures, whereas in the other two groups ToC and textual macro-structures diverge from each other in various ways. The analysis also shows a high degree of similarity between relation cues at the textual micro- and macro-levels. The results are discussed with respect to genre differences, student writers’ generic competence and institutional factors of students’ text production.

The existing discourse parsing systems make use of different theories to put at the basis of processes of building discourse trees. Many of them use Recall, Precision and F-measure to compare discourse tree structures. These measures can be used only on topologically identical structures. However, there are known cases when two different tree structures of the same text can express the same discourse interpretation, or something very similar. In these cases Precision, Recall and F-measures are not so conclusive. In this paper, we propose three new scores for comparing discourse trees. These scores take into consideration more and more constraints. As basic elements of building the discourse structure we use those embraced by two discourse theories: Rhetorical Structure Theory (RST) and Veins Theory, both using binary trees augmented with nuclearity notation. We will ignore the second notation used in RST – the name of relations. The first score takes into account the coverage of inner nodes. The second score complements the first score with the nuclearity of the relation. The third score computes Precisions, Recall and F-measures on the vein expressions of the elementary discourse units. We show that these measures reveal comparable scores there where the differences in structure are not doubled by differences in interpretation.Keywordsdiscourse parserRhetorical Structure TheoryVeins Theoryevaluationdiscourse tree structure

이 연구는 전문 필자의 문장이 다른 필자의 문장에 비해 짧다는 점에 착안하여, 연결어미가 문맥에서 가지는 역할과 의미를 보다 구체적으로 분석해 보는 데에 그 목적이 있다.BR 실제 언어생활에서 화자는 ‘문맥’을 고려하여 연결어미나 종결어미를 사용한다. 이에 따라 연결어미의 의미를 ‘담화 · 텍스트’ 차원에서 분석하고자 전문 필자가 쓴 글인 ‘칼럼’을 대상으로, ‘담화 · 텍스트’를 분석하는 도구 중 하나인 ‘수사구조이론(RST)’을 적용하여 ‘연결어미’가 쓰인 문맥의 수사 의미 관계를 분석해 보았다.BR 칼럼에 제시된 ‘-고’는 연결어미 중 가장 많이 쓰였다. ‘-고’는 대등하게 두 사실을 연결하는 의미이나 보다 구체적으로 ‘상세설명(Elaboration)’, ‘의도적 결과(Volitional Result)’, ‘연속(Sequence)’, ‘대조(Contrast)’, ‘배경(Background)’, ‘증거(Evidence)’, ‘연결(joint)’의 7가지 수사 의미 관계로 쓰이며, ‘연속(Sequence)’의 의미 관계로 가장 많이 쓰였다. ‘-지만’은 앞의 내용과 반대되는 내용을 말한다는 의미를 가지므로, ‘대조(Contrast)’의 의미로 쓰일 것으로 예상되지만, 실제로 ‘대비(Antithesis)’와 ‘양보(Concession)’의 문맥에서 주로 쓰였다. ‘-(으)며’는 ‘연결(joint)’의 문맥뿐만 아니라 보다 구체적으로 ‘상세설명(Elaboration)’이나 ‘증거(Evidence)’ 등의 수사 의미 관계를 갖는 문맥에도 쓰였다. 또 ‘연결(joint)’의 문맥에서 ‘-(으)며’와 ‘-고’가 함께 쓰인다는 것을 알 수 있었다.BR 이 연구는 분석 칼럼 수가 적고 타당성 검증이 이루어지지 않았다는 한계를 가지고 있으나, 전문 필자들이 연결어미를 쓰는 문맥과 그러한 문맥이 갖는 의미를 분석했다는 점, 응용 언어학 분야에 도움이 될 수 있다는 점에서 의의가 있을 수 있다.

This paper identifies a major problem in planning discourse, and then points to a solution. The problem is that of the relationship between models for monologue and dialogue. Rhetorical structure theory (RST) is selected as the current best prospect for modelling monologue. A model for exchange structure is then outlined — the systemic flowchart model — and we conclude by showing how the two can be related to each other in an integrated overall model.

Emotion-Cause Pair Extraction (ECPE) aims to identify and extract emotion clauses and their corresponding cause clauses from unannotated emotional texts. Previous approaches primarily leveraged contextual features or attention weights as semantic information to enhance feature representations. However, these methods often overlook the additional causal information that external knowledge can bring to ECPE. Given the evident inferential relationship between emotions and their causes, we propose a novel model called Rhetorical Structure Theory and Inference-Aware Graph networks (RSTIAG) to address the challenges posed by ECPE. This model constructs a semantic dependency space grounded in discourse-level rhetorical structure theory and a symbolic reasoning space based on an inference-aware graph. By integrating the introduced knowledge through a space fusion co-attention mechanism and modeling the dependencies between these two spaces, the model enables clauses to simultaneously capture diverse knowledge from both spaces. Additionally, we enrich the information dimensions of emotion-cause pairs by instantiating the reasoning process from the perspectives of causality and implicit inference. To substantiate the effectiveness of our proposed RSTIAG model, we undertake comprehensive experiments. The results demonstrate that it significantly outperforms 11 baseline models on an English benchmark corpus, confirming its effectiveness.

These definitions and protocols are intended as an online supplement to work in the course of publication. This work focuses on the tagging of corpora of argumentative writing with logical relations, and presents the frameworks used in the text analysis at the base of the tagging.

Rhetorical relations in university students’ presentations

Discourse structures have a central role in several computational tasks, such as question-answering or dialogue generation. In particular, the framework of the Rhetorical Structure Theory (RST) offers a sound formalism for hierarchical text organization. In this article, we present HILDA, an implemented discourse parser based on RST and Support Vector Machine (SVM) classification. SVM classifiers are trained and applied to discourse segmentation and relation labeling. By combining labeling with a greedy bottom-up tree building approach, we are able to create accurate discourse trees in linear time complexity. Importantly, our parser can parse entire texts, whereas the publicly available parser SPADE (Soricut and Marcu 2003) is limited to sentence level analysis. HILDA outperforms other discourse parsers for tree structure construction and discourse relation labeling. For the discourse parsing task, our system reaches 78.3% of the performance level of human annotators. Compared to a state-of-the-art rule-based discourse parser, our system achieves a performance increase of 11.6%.

William C. Mann passed away on August 13, 2004, after a long struggle with leukemia. He is known to readers of Computational Linguistics as a keen supporter and past president (1987) of ACL, a pioneer in the development of text generation as a field of research in computational linguistics, the originator of rhetorical structure theory (RST) and dialogue game theory (DGT), and the developer (together with David Weber) of dialect adaptation as a technique within machine translation. And he’ll be remembered for these and many other contributions, but above all, in this context, he’ll be remembered as a unique visionary in computational linguistics (CL) and as a truly wonderful and extraordinarily generous colleague. Bill Mann made huge contributions to many people’s intellectual development, to their careers, and to their lives in general. What follows are my own recollections of him, selected from a crowded jungle of memories. I will leave it to others to fill out the picture, but I shall attempt to give an indication of the intellectual and historical context in which Bill was working and also of the network of researchers that he created; his ideas have radiated throughout this network of scholars around the world. I met Bill in April 1980 and worked as a research linguist on a succession of projects he directed, or codirected, at the Information Sciences Institute (ISI) at the University of Southern California (USC), until I left the institute to take up a position at the University of Sydney in August 1988. Through that period (which happened to coincide, more or less, with the Reagan years), not only was Bill a very wise and wonderful project leader, but he also became a mentor and guide and a true friend. I followed from afar the further developments in his life: his departure from ISI and move to Kenya with his family to take up a position with the Summer Institute of Linguistics (SIL) as a consultant responsible for work on discourse and computational matters, their return to the United States, and his new phase of research with initiatives in RST and DGT.

We introduce a novel top-down end-to-end formulation of document-level discourse parsing in the Rhetorical Structure Theory (RST) framework. In this formulation, we consider discourse parsing as a sequence of splitting decisions at token boundaries and use a seq2seq network to model the splitting decisions. Our framework facilitates discourse parsing from scratch without requiring discourse segmentation as a prerequisite; rather, it yields segmentation as part of the parsing process. Our unified parsing model adopts a beam search to decode the best tree structure by searching through a space of high-scoring trees. With extensive experiments on the standard English RST discourse treebank, we demonstrate that our parser outperforms existing methods by a good margin in both end-to-end parsing and parsing with gold segmentation. More importantly, it does so without using any handcrafted features, making it faster and easily adaptable to new languages and domains.

This study investigates the (re)creation of rhetorical structure, a crucial aspect of coherence that plays an important part in establishing functional equivalence in translation. While considerable amount of research is available on certain aspects of coherence, little attention has been devoted to the translation of rhetorical structure, despite its acknowledged significance in discourse processing (Hatim and Mason 1990, Mann et al. 1992, Nord 1997, Tirkkonen-Condit 2002). Based on Rhetorical Structure Theory (Mann and Thompson 1986), this study aims to generate initial hypotheses regarding the (re)creation of rhetorical structure in Hungarian-English news translation and demonstrate the interplay between rhetorical and discourse structure, with a view to highlighting the significance of rhetoric in producing functionally adequate translations. Findings indicate that while no statistically significant shifts occur in the quantity of relational propositions in source texts and translations, considerable shifts may be identified in the quality and position of certain relational propositions . These shifts affect the rhetorical as well as generic structure of the target text and thus exert a very subtle influence on the way it is interpreted by the reader.