No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Automated Approach to Rhythm Figures Search in English Text
Abstract
Text rhythm is recognized as being one of the most important subject areas of modern linguistic studies. There is a considerable amount of literature on the analysis of rhythm in poetry and literary prose. However, few researchers have addressed the problem of using automated tools for rhythm analysis, whereas automated methods can be of great benefit to this cause, especially when the research is conducted on large text corpora. This paper presents a new automated approach to integrated search of rhythm figures in fiction including anaphora, epiphora, anadiplosis, symploce and simple repetition provided for by an original lexical tool designed within the framework of the research. The ad hoc experiments have proved this approach to be reliable and informative.
... The quality of algorithms of figures search was measured by an expert in linguistics. The methodology of expert analysis and quality of previous versions of algorithms was described in more detail in our paper [21]. Four researchers processed a total of 24 texts of different authors, randomly selected from the corpus. ...
The paper is devoted to automatic detection of rhythm in fiction and investigation of how rhythm of prosaic texts changed over 19th-21st centuries, based on results of such detection. The authors developed algorithms, which extract rhythm figures related to word repetitions (anaphora, epiphora, polysyndeton, etc.), and visualized their statistical features in plots and heat maps by decades on the material of British and Russian literature. The experiments allowed to find rhythm changes over periods and give interpretation of their reasons from a linguistic point of view.
The article examines the linguistic specificity of the text of African literary tales on the basis of the material of “African Legends” by Bernard Dadier. The analysis reveals a close interrelation between the meanings and the linguistic component of the narrative that results in the formation of a matrix of expressive means, built up by various elements of textual cohesion. The analysis is carried out in the context of the communicative-discursive approach. It is based on theoretical studies on the linguistic specificity of African narratives, previously carried out by Russian, French and Ivorian researchers, as well as on the analyses of works devoted to the issues of cohesion and coherence, which serve the integrity of the text, the interrelation of meanings and linguistic means. The main objective of the study is to identify the main characteristics of Ivorian tales in general and of tales about the Ivorian people reflected in the collection of legends by Bernard Dadier, a famous Ivorian writer and screenwriter, in particular. The main research methods include intertextual, semantic-stylistic and motive analysis, as well as the “word-image” method, which seem to be most relevant for examining the author's approach to achieving coherence and highlighting the musicality and rhythmicity of the tales. From the study, the authors conclude that the cohesion of the discourse of Ivorian literary tales is mainly achieved through the use of uncomplicated homogeneous elements and diacope, the repetition of words at certain intervals within a sentence or at the junction of short sentences / clauses. Less productive are gradation and gradational repetition, as well as reduplication and anadiplosis. However, these devices often complement the images created by the author
The paper assesses and evaluates the performance of the ProseRhythmDetector (PRD) Text Rhythm Analysis Tool. The research is a case study of 50 English and 50 Russian fictional texts (approximately 88,000 words each) from the 19th to the 21st century. The paper assesses the PRD tool accuracy in detecting stylistic devices containing repetition in their structure such as diacope, epanalepsis, anaphora, epiphora, symploce, epizeuxis, anadiplosis, and polysyndeton. The article ends by discussing common errors, analysing disputable cases and highlighting the use of the tool for author and idiolect identification.
Rhetorical figures are valuable linguistic data for literary analysis. In this article, we target the detection of three rhetorical figures that belong to the family of repetitive figures: chiasmus (I go where I please, and I please where I go.), epanaphora also called anaphora (“Poor old European Commission! Poor old European Council.”) and epiphora (“This house is mine. This car is mine. You are mine.”). Detecting repetition of words is easy for a computer but detecting only the ones provoking a rhetorical effect is difficult because of many accidental and irrelevant repetitions. For all figures, we train a log-linear classifier on a corpus of political debates. The corpus is only very partially annotated, but we nevertheless obtain good results, with more than 50% precision for all figures. We then apply our models to totally different genres and perform a comparative analysis, by comparing corpora of fiction, science and quotes. Thanks to the automatic detection of rhetorical figures, we discover that chiasmus is more likely to appear in the scientific context whereas epanaphora and epiphora are more common in fiction.
Rhythm analysis of written texts focuses on literary analysis and it mainly considers poetry. In this paper we investigate the relevance of rhythmic features for categorizing texts in prosaic form pertaining to different genres. Our contribution is threefold. First, we define a set of rhythmic features for written texts. Second, we extract these features from three corpora, of speeches, essays, and newspaper articles. Third, we perform feature selection by means of statistical analyses, and determine a subset of features which efficiently discriminates between the three genres. We find that using as little as eight rhythmic features, documents can be adequately assigned to a given genre with an accuracy of around 80 %, significantly higher than the 33 % baseline which results from random assignment.
Rhythm analysis is widely used for texts in a poetic form to determine the individual style of the author, but rarely used in the analysis of prose due to technical problems and human factor influence. To overcome these issues we propose an automated approach that involves the development and use of specialized software for analyzing French literary prose at various stylistic levels: phonetic, lexical, and grammatical. The methods developed for rhythm analysis and implemented in the computer application cover a variety of the phonostylistic devices: calculation of the length of the rhythmic units, finding assonance, alliteration, rhyme, various repetitions, and others. Efficiency of the approach was proved experimentally by the analysis of rhythmization devices in the novels of four French writers. It was shown that the proposed automated approach allows the researcher to analyze the text 15 times faster than using the manual approach.
We employ statistical methods to analyze, generate, and translate rhythmic poetry. We first apply unsupervised learning to reveal word-stress patterns in a corpus of raw poetry. We then use these word-stress patterns, in addition to rhyme and discourse models, to generate English love poetry. Finally, we translate Italian poetry into English, choosing target realizations that conform to desired rhythmic patterns.
Analysis of features of rhythmic structure of texts of different styles of the speech
- L Kishalova
Introduction à l’analyse stylistique
- C Fromilhague
- A Sancier-Chateau
Vocabulaire de l’analyse littéraire
- D Bergez
- V Géraud
- J J Robrieux
Pae stylistique informatique. Computer stylistic
- P Couranjou
- B Lachambre
Anthropologie historique du langage. Verdier: coll. “Verdier Poche
- H Meschonnic
Rhythm analysis in chats using natural language processing
- I D Niculescu
- S Trausan-Matu
Poétique de la prose ou prose poétique? le rythme contre le prosaïsme. Questions de style, Vous avez dit prose? pp
- S Freyermuth
A critical comparison of rhythm in music and natural language
- M Balint
- S Trausan-Matu
Analyzer of the rhythmic structure of the text: attribution of texts based on rhythmical patterns
- K Belousov
- G Dusakova