Content uploaded by Chrysanne Di Marco
Author content
All content in this area was uploaded by Chrysanne Di Marco on Jan 13, 2015
Content may be subject to copyright.
A preview of the PDF is not available
Constructing a Rhetorical Figuration Ontology
Abstract and Figures
Many essential components of language charted by rhetoric, the ancient study of persuasion, remain understudied and underrepresented in current Natural Language systems. Our goal is to combine linguistic and rhetorical theories with discourse analy- sis and machine learning to develop formal models of computational rhetoric that may be usefully applied in real-world Computational Linguistics systems. As part of this initiative, we are building an on- tology of rhetorical figures and formalizing their expression.
Figures - uploaded by Chrysanne Di Marco
Author content
All figure content in this area was uploaded by Chrysanne Di Marco
Content may be subject to copyright.
... While both of these works include passing mentions of rhetorical figures, and Grasso emphasises their importance for "creating a computational model of rhetorical argumentation" [17] any indication of how such a project might proceed. The first work to impose some computational order on figures was initiated by Harris and Di Marco [18]. This ongoing thread of research has more recently started to deliver results that can lay a foundation for detailed text processing (see, e.g., Mladenović and Mitrović's application to Serbian [28], and Gladkova's broader 'conspiracy of features' approach to argument diagnostics [16]), and the mining of rhetorical figures [15,21]. ...
... The computational detection of rhetorical figures is tremendously promising, as Crosswhite et al. [9], Grasso [17], Harris and Di Marco [18], and Ruan et al. [36], among others, seem to agree. It remains nevertheless an equally undeveloped area. ...
... Fahnestock[12] discusses such issues relating to antithesis, as well as 'double antitheses', in detail (pp. 45-85).18 An annotated version of Example (8) is available in OVA at arg.tech/ova-5627.[research-article] ...
The generalised, automated reconstruction of the reasoning structures underlying persuasive communication is an enormously challenging task. While this work in argument mining is increasingly informed by the rich tradition of argumentation studies outside the computational field, the rhetorical perspective on argumentation is thus far largely ignored. To explore the application of rhetorical insights in argument mining, we conduct a pilot study on the connection between rhetorical figures and argumentation structure. Rhetorical figures are linguistic devices that perform a variety of functions in argumentative discourse. The textual form of some of these figures is easy to identify automatically, such that an established connection between the figure and a preponderance of argumentative content would improve the performance of argument mining techniques. Furthermore, the automated mining of rhetorical figures could be used as an empirical, corpus-based testing ground for the claims made about these figures in the rhetorical literature. In the pilot study, we explore the connection between eight rhetorical figures the forms of which we expect to be relatively easy to identify computationally, and argumentation structure (concretely, we consider the six schemes 'anadiplosis', 'epanaphora', 'epistrophe', 'epizeuxis', 'eutrepismus', and 'polyptoton', and the two tropes 'antithesis' and 'dirimens copulatio', and relate their occurrences to relations of inference and conflict). The data of the study is collected in the MM2012c corpus of 39,694 words of argumentatively annotated transcripts from the BBC Radio 4's MoralMaze discussion program.We show that some of the figures indeed correspond to passages of high argumentative density, relative to the text as a whole..
... The Rhetorical RST Ontology layer of this framework consists of three major sides, as diagrammed in Fig. 1: (i) coherence relations side that models elements (e.g., claims or supports) and the relations connecting them (e.g., Antithesis, Circumstance, Concession or Purpose); (ii) rhetorical blocks side that provides a coarse-grained structure for modeling the discourse (e.g., abstract, motivation, background or conclusion); (iii) argument side that captures the argument present in the publication via concepts like Issue, Position or Argument. This Rhetorical layer can be enriched with ontologically modeled separate rhetorical figures to enable fine-grained annotations of rhetorical figures which play an important part in arguments, following approaches to figurational modeling used in [22,32] and [58], as well as our approach to modeling rhetorical figures, as described in Section 3.2 of this paper. ...
... A formal domain ontology of rhetorical figures for Serbian (The RetFig ontology) presented in [48] is a formal realization of the programs sketched in [32] and [35]. These programs were the basis for the development of methods and tools for automatic detection and annotation of rhetorical figures, as presented in [21,34,60] and [15]. ...
This paper surveys ontological modeling of rhetorical concepts, developed for use in argument mining and other applications of computational rhetoric, projecting their future directions. We include ontological models of argument schemes applying Rhetorical Structure Theory (RST); the RhetFig proposal for modeling; the related RetFig Ontology of Rhetorical Figures for Serbian (developed by two of the authors); and the Lassoing Rhetoric project (developed by another of the authors). The Lassoing Rhetoric venture is interesting for its multifaceted approach to linguistic devices, prominently including rhetorical figures, but also RST relations and stylistic models, like the use of historic present. This application takes a natural language text input and uses syntactic parsing tools to produce a knowledge base of linguistic entities using references to an OWL ontological framework, locating these devices using Semantic Web Rule Language (SWRL) logic rules. The paper also reports on a similar approach in research into detecting ironic tweets in a Serbian twitter corpus. The rhetorical schemes used for argument mining are also presented, as well as some suggestions for novel argument schemes based on the ontological approach to rhetorical figuration.
... Indeed, one is reluctant to trust computer assistance when it comes to judging the rhetoric of a text. As expressed by Harris and DiMarco (2009): Too much attention has been placed on semantics at the expense of rhetoric (in-cluding stylistics, pragmatics, and sentiment). While computational approaches to language have occasionally deployed the word 'rhetoric', even in quite central ways (such as Mann and Thompsons Rhetorical Structure Theory (1988)), the deep resources of the millenia-long research tradition of rhetoric have only been tapped to a vanishingly small degree. ...
... The identification of chiasmus is not very common in computational linguistics, although it has sometimes been included in the task of detecting figure of repetition (Gawryjolek, 2009;Harris and DiMarco, 2009;Hromada, 2011). Gawryjolek (2009) proposes to extract every pair of words repeated in reverse order in the text, but this method quickly becomes impractical with big corpora. ...
... In Computer Science, the situation is little better. The case has been made, dating to the turn of the century, that computational argument studies have a rich potential to investigate figures ( [8,9,25,54]), and there is growing success in the detection of rhetorical figures ( [12,13,23,24,29,31,50,58]). But, until this volume and the groundbreaking work of Lawrence, Visser, and Reed, these two strains -the detection of the forms and the study of argumentative functions -have not been brought together. ...
... In the study of figurative language semantic networks such as WordNet (Mason 2004; Barbieri, Ronzano and Saggion 2015), ontology (Harris and Di Marco 2009; Kelly et al. 2010), lexical resources such as corpora (Mason 2004; Hao and Veale 2010;Rosso 2012a), specialized dictionaries of emoticons and punctuation (Carvalho et al. 2009; Gonz?lez-Ib??ez et al. 2011; Barbieri, Ronzano and Saggion 2015) and lexicons like SentiWordNet (Rentoumi et al. 2010; Gonz?lez-Ib??ez et al. 2011; Barbieri, Ronzano and Saggion 2015) play an important role. In this paper we propose a method of automatic recognition of rhetorical figures belonging to the group of tropes, using the rules defined in an ontology SWN which is based on the Serbian semantic network WordNet. ...
Automatic recognition of rhetorical figures (similes, irony, sarcasm, humor, metaphors, etc.) is increasingly used in natural language processing tasks, primarily to improve sentiment classification, machine translation, but also for analysis of linguistic structures on different levels. In this paper, we propose a method of automatic recognition and classification of rhetorical figures from the group of tropes that uses ontological inference rules in an ontology based on Serbian WordNet (SWN). A binary classification method was carried out on the rhetorical figure simile and evaluated by ROC curve (AUC = 0.696) which indicates that it can be successfully used in solving these types of tasks. We also propose a semi-automatic ontology learning method, for further learning of SWN ontology, by increasing the number and the type of relationships that can assist in the detection of figurative language in the texts in Serbian.
Rhetorical figures are form/function alignments in which the form (1) serves to convey the function(s) and (2) supports their computational detection; therefore, (3) they are particularly rich for various text mining activities and other Natural Language Understanding purposes. The figures which are especially valuable in these ways are known as schemes, figures that are defined by their material (phonological, orthographical, morpholexical, or syntactic) form, in distinction particularly from tropes, which are defined by their conceptual (semantic) form. Rhetorical schemes, however, have been almost universally ignored by linguists, including computational linguists. This article illustrates form/function alignments for a small handful of rhetorical schemes, with some examples of how they communicate specific meanings. The communicative functions of rhetorical schemes rely not so much on individual schemes as on certain collocations of schemes (sometimes with tropes or other figures as well). These collocations, in turn, are coordinated by linguistic features such that the relevant expressions fit the notion of a construction as understood in the Construction Grammar framework. Examples are drawn from epanalepsis, as well as antimetabole, mesodiplosis, and parison, which collate frequently as a group and also collectively with the trope, antithesis. The communicative functions explored include Semantic-Feature Promotion, Reciprocal Specification, Reciprocal Energy, Irrelevance of Order/Rank, Subclassification, and Reject-Replace. Rhetorical figure detection is also discussed in some detail with respect to figural and grammatical collocation.
This article presents two methods for the automatic generation of application ontologies from the multilingual BalkaNet WordNets Web ontology language (OWL) representation. Both proposed methods are applied on the BalkaNet WordNets ontology for the Serbian language (SerWN). The first one uses only the SerWN, both for generating class hierarchy and instances of classes, while the other method combines the SerWN with a domain ontology. The first method was used to automatically generate the FoodOntology, whereas the second method to generate the ontology of rhetorical figures tropes. Preliminary evaluation results corroborate the soundness of the approach. Since BN consists of individual WNs for five Balkan languages and Czech, the methodology presented in this article can also be used for all these languages. The first method can also be used for other domains.
Identifying rhetorical figures with marginal to non-existent lexico-syntactic signatures poses significant challenges for computational approaches reliant upon structural definitions or descriptions. One such figure is prolepsis (φpoλ n ψ) which this essay charts out in some detail, addressing the challenges and the benefits of rendering such figures computationally tractable through the use of argument schemes with attention to metadiscursive or macro-discursive norms offered by pragma-dialectical traditions.
The paper reports on the results of an exploratory study into the topical organisation and stylistic features of argumentation in a corpus of ophthalmic clinical research papers. The study responds to the need for systematised and generalisable argumentation models in knowledge-intensive fields. We present here a schematised superstructure of the arguments from the corpus, charting the configurations of stylistic features, which signal the elements of this superstructure, epistemic topoi. We pay special attention to the role of lexical categories (or semantic fields) in the configurations, to the relations between the fields, and to their interactions with other elements of the configurations, including semantic, grammatical, syntagmatic, deictic, and coreferential features. Epistemic topoi are a promising discourse constituent in argumentation because, as we found, they are distinct from syntagmatic units, such as phrases, clauses, or argumentative zones, and because they are signalled with substantially distinctive stylistic features despite having no fixed order in the superstructure. They hold considerable promise for computational argumentation analysis and processing, perhaps especially in scientific and technical discourses, where the need for reliable detection and summarisation is particularly high. Our investigation shows that despite the complex and interpenetrating
semantic and stylistic attributes of argumentation, there are significant, computationally tractable regularities.
Editorials represent opinion articles written by the publisher, editors or columnists of newspapers. From this perspective, editorials are ideal sources for outlining views on events and analyzing how they are perceived, e.g. whether they are positive or negative or the kind of feelings or analysis they involve (uncertainty, worries, etc.). The proposed work aims at identifying the linguistic criteria and at creating a model for the aforementioned purpose, which makes use of an adequate set of semantic tags that we have defined to annotate texts from which a detailed analysis can be carried out.
The project, HANDS (Helping Autism-diagnosed teenagers Navigate and Develop Socially), studies how teenagers with ASD and with IQ within the normal range (IQ > 70) can handle what they see as difficult situations using mobile technology. HANDS is a project sponsored by the European Commission as part of the 7th Framework Programme. It is the basic hypothesis in HANDS that it is possible to improve quality of life for teenagers with ASD by providing a mobile ICT toolset supporting them in many daily situations. In this paper, it is argued that a careful conceptual analysis of the idea of "handling difficult situations" can be very useful as a basis for understanding the potential in a system supporting teenagers with ASD. It is also argued that such a conceptual analysis can be based on a combinations of i) psychological insights regarding teenagers with ASD, ii) so-called "usage narratives" describing difficult situations for teenagers with ASD, and iii) central ideas from temporal logic describing formally what it could mean to handle a difficult situation. Furthermore, it is argued that the conceptual analysis can be combined with ideas from so-called persuasive design (PD) in a very straightforward manner. It is finally shown that this conceptual analysis gives rise to a rather strong argument for certain specific system requirements regarding the future HANDS toolset.
This critical review assesses whether evaluation studies can answer three key questions about behaviour change interventions: 'Do they work? How well do they work? How do they work?' Reviews of intervention evaluations are examined, particularly those addressing decreasing unprotected sexual intercourse and smoking. Selection of outcome measures and calculation of effect sizes are discussed. The article also considers the extent to which evaluation reports specify (i) discrete intervention techniques and (ii) psychological mechanisms that account for observed behavioural change. It is concluded that intervention descriptions are often not specific about the techniques employed and that there is no clear correspondence between theoretical inspiration and adoption of particular change techniques. The review calls for experimental testing of specific theory-based techniques, separately and in combination.
Computer Supported Argument Visualization is attracting attention across education, science, public policy and business. More than ever, we need sense-making tools to help negotiate understanding in the face of multi-stakeholder, ill-structured problems. In order to be effective, these tools must support human cognitive and discursive processes, and provide suitable representations, services and user interfaces. Visualizing Argumentation is written by practitioners and researchers for colleagues working in collaborative knowledge media, educational technology and organizational sense-making. It will also be of interest to theorists interested in software tools which embody different argumentation models. Particular emphasis is placed on the usability and effectiveness of tools in different contexts.
Among the key features are:
- Case studies covering educational, public policy, business and scientific argumentation
- Expanded, regularly updated resources on the companion website:
www.VisualizingArgumentation.info
"The old leadership idea of "vision" has been transformed in the face of wicked problems in the new organizational landscape. In this excellent book we find a comprehensive yet practical guide for using visual methods to collaborate in the construction of shared knowledge. This book is essential for managers and leaders seeking new ways of navigating complexity and chaos in the workplace."
(Charles J. Palus, Ph.D, Center for Creative Leadership, Greensboro, North Carolina, USA)
This paper presents an overview of the field of recommender systems and describes the current generation of recommendation methods that are usually classified into the following three main categories: content-based, collaborative, and hybrid recommendation approaches. This paper also describes various limitations of current recommendation methods and discusses possible extensions that can improve recommendation capabilities and make recommender systems applicable to an even broader range of applications. These extensions include, among others, an improvement of understanding of users and items, incorporation of the contextual information into the recommendation process, support for multicriteria ratings, and a provision of more flexible and less intrusive types of recommendations.
Within the European Community both the environmental and safety costs of road transport are unacceptably high. ‘Foot-LITE’ is a UK project which aims to encourage drivers to adopt ‘greener’ and safer driving practices, with real-time and retrospective feedback being given both in-vehicle and off-line. This paper describes the early concept development of Foot-LITE, for which a Cognitive Work Analysis (CWA) was conducted. In this paper, we present the results of the first phase of CWA – the Work Domain Analysis, as well as some concept interface designs based on the WDA to illustrate its application. In summary, the CWA establishes a common framework for the project, and will ultimately contribute to the design of the in-vehicle interface
Poor sitting habits and bad sitting posture are often the cause for musculoskeletal disorders like back pain. Also office employees are affected, because they carry out the majority of their work sitting in front of computers. Therefore we aim at sensitizing and motivating office employees regarding preventive healthcare. We have developed a persuasive interface in form of an interactive picture frame which integrates unobtrusively into the working environment --- the perFrame. This frame contains a moving portrait of a person the employee loves or likes. It provides affective feedback in order to persuade employees for better sitting habits while working with a computer. We conducted a preliminary in-situ study, deploying these picture frames on the desktops of eight office employees. The results highlight the employees' acceptance of our application as well as its potential to foster awareness and achieve persuasion regarding healthy behavior in the office.