Rhetorical Figure Detection: the Case of Chiasmus
Open accessThe DOI matches its Crossref record; 14 of the 15 references it cites were found in a registry or an index; none of the 17 sources its claims cite is checked for support yet.
Abstract
We propose an approach to detecting the rhetorical figure called chiasmus, which involves the repetition of a pair of words in reverse order, as in "all for one, one for all".Although repetitions of words are common in natural language, true instances of chiasmus are rare, and the question is therefore whether a computer can effectively distinguish a chiasmus from a random criss-cross pattern.We argue that chiasmus should be treated as a graded phenomenon, which leads to the design of an engine that extracts all criss-cross patterns and ranks them on a scale from prototypical chiasmi to less and less likely instances.Using an evaluation inspired by information retrieval, we demonstrate that our system achieves an average precision of 61%.As a by-product of the evaluation we also construct the first annotated corpus of chiasmi.
Overview
CoChat Summary
TL;DR
The paper proposes treating chiasmus detection as a graded ranking problem rather than binary classification, using a linear model over four feature groups to rank criss-cross word repetitions. On a Europarl test set, the best system reaches 61% average precision and 90% recall among 19 manually identified true positives.
Key findings
- The best model (“+Lexical clues”) achieves average precision of 61%, with precision at top 10, 50, 100, and 200 candidates of 70%, 28%, 17%, and 9%, respectively.
- Adding size features finds 14 of 19 chiasmi within the top 200 hits (74% recall); adding N-gram similarity raises this to 17 of 19 (90% recall), while lexical clues improve precision slightly without increasing recall.
- At candidate rank 9, the proposed system has precision 78%, recall 37%, and F1 59%, compared with Hromada (2011) at precision 67%, recall 32%, F1 43%, and Gawryjolek (2009) at 0% precision and recall.
- The system processes one million words in 214 seconds, about three times slower than Hromada’s 78 seconds per million words, and the work also produces 1200 manually annotated criss-cross patterns as true, false, or borderline cases.
Methods
- Experiments use English Europarl, split into two two-million-word extracts: one tuning corpus and one held-out test corpus.
- The system tokenises and lemmatises with TreeTagger, extracts every pair of repeated and inverted lemmas within a 30-token window, and scores candidates with a linear model using 20 features in four groups: basic stopword/punctuation, size, N-gram similarity, and lexical clues.
- Weights are set empirically by observing successive results on the tuning set; evaluation manually annotates the top 200 hits from each experiment and reports precision-recall graphs and average precision.
Limitations
- The paper states that because of the small number of positive examples, only tentative conclusions can be drawn and the results might not be statistically significant.
- The paper states that manual tuning means not every possible weight combination was tried, and that no existing annotated data prevented supervised machine learning or absolute recall estimation.
- Evident from the text: evaluation is limited to English political discourse from Europarl, recall is estimated from only 19 true positives found through top-200 annotations across four experiments, borderline cases are excluded from results, and annotation relies on human intuition because no clear discriminative test for chiasmus is stated.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures
Verification
Claims the paper makes
0 Valid · 2 Not valid · 14 Not checked · 24 Own results and interpretations
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Using an evaluation inspired by information retrieval, we demonstrate that our system achieves an average precision of 61%.”
- Also stated in: § (3) Each throat was parched , and glazed each eye . · plain
“According to our evaluation, inspired from information retrieval methodology, our system gets up to 61% average precision.”
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § (3) Each throat was parched , and glazed each eye . · plain
In the paper
“We run the experiment of Hromada (2011) on our test set. 6 It outputs 6 true positives for a total of only 9 candidates.”
What the sources say
- Not matchedcites Hromada (2011)
An author–year citation the paper’s reference list doesn’t settle. We don’t search these by name.
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As a by-product of the evaluation we also construct the first annotated corpus of chiasmi.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As a side effect we provide a partially annotated tuning set with 1200 extracts manually annotated as true or false chiasmus instances.”
- Also stated in: § 6 Conclusion · plain
“We kept track of all annotations and thus our fourth contribution is a set of 1200 criss-cross patterns manually annotated as true, false and borderline cases, which can be used for training or evaluation or both.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 6 Conclusion · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We notice, indeed, a significant progression of the number of chiasmi if we use N -gram similarity features (17 out of 19 chiasmi).”
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
10 more claims
Create a free account to see all 40 claims and every source verdict.
- It may state two separate claims as one. 16
- Probably not a substantial claim. 11
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“To give an idea of the rarity, in Dubremetz and Nivre (2015) we give the example of River War by Winston Churchill, a book consisting of 150,000 words, with 66,000 examples of criss-cross patterns but only one real chiasmus 4 .”
From Rhetorical Figure Detection: Chiasmus, Epanaphora, Epiphora (2018) · cites this paper as Dubremetz and Nivre (2015)
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“A serious methodological problem for the evaluation of chiasmus detection is the massive concentration of false positives (about 66,000 of them for only one true positive in 150,000 words).”
From Rhetorical Figure Detection: Chiasmus, Epanaphora, Epiphora (2018) · cites this paper as Dubremetz and Nivre (2015)
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Second, as shown in Dubremetz and Nivre (2015) those figures playing on repetition of words can be rare, or even extremely rare (sometimes only one figure is to be found in several hundred pages of books).”
From Rhetorical Figure Detection: Chiasmus, Epanaphora, Epiphora (2018) · cites this paper as Dubremetz and Nivre (2015)
The cited source says what the claim attributes to it.
In the citing paper
“We observed that chiasmus, like metaphor (Dunn, 2013), can be seen as a graded phenomenon with prototypical examples and controversial/borderline cases.”
From Rhetorical Figure Detection: Chiasmus, Epanaphora, Epiphora (2018) · cites this paper as Dubremetz and Nivre (2015)
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
§ 5.3 Evaluation
“| F 1 -Score | 59 | 0 | 43 |”
§ 5.3 Evaluation
“| Precision | 78 | 0 | 67 | | Recall | 37 | 0 | 32 |”
Citations
Cites
Rhetorical Structure Theory: Toward a functional theory of text organization
MANN, W. C., & THOMPSON, S. A. (1988) · Text - Interdisciplinary Journal for the Study of Discourse · doi:10.1515/text.1.1988.8.3.243 · Cited by 3,853
The Princeton Encyclopedia of Poetry and Poetics
Greene, R. A., Cushman, S., Cavanagh, C., Ramazani, J., & Rouzer, P. (2012) · Princeton University Press eBooks · doi:10.1515/9781400841424 · Cited by 447
Fontanier, P., & Genette, G. (1968) · CERN Document Server (European Organization for Nuclear Research) · Cited by 281
Estimating the recall performance of Web search engines
Clarke, S. J., & Willett, P. (1997) · Aslib Proceedings · doi:10.1108/eb051463 · Cited by 120 · cited 1×
“For instance Clarke and Willett (1997, p.186), working with Altavista, Lycos and Excite, made a pool of relevant documents for a particular query by merging the outputs of the three engines.”
Background(1961) · Presses Universitaires de France eBooks · Cited by 57
A Tale of Two Cultures: Bringing Literary Analysis and Computational Linguistics Together
Hammond, A., Brooke, J., & Hirst, G. (2013) · North American Chapter of the Association for Computational Linguistics · Cited by 41
The Princeton Encyclopedia of Poetry and Poetics: Fourth Edition
Greene, R. A., Cushman, S., Cavanagh, C., et al. (2012) · Cited by 40
The internet and information retrieval research: a brief review
Chowdhury, G. G. (1999) · Journal of Documentation · doi:10.1108/eum0000000007144 · Cited by 30 · cited 1×
“As described already fifteen years ago by Chowdhury (1999, p.213), in such a situation calculating the absolute recall is impossible.”
BackgroundAutomated Annotation and Visualization of Rhetorical Figures
Gawryjołek, J. (2009) · UWSpace (University of Waterloo) · Cited by 17
(2011) · Cited by 13
Research works printed but not linked: 3
- Marie Dubremetz. 2013. Vers une identification automatique du chiasme de mots. In Actes de la 15e Rencontres des ´ Etudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RECITAL'2013) , pages 150-163, Les Sables d'Olonne, France.
- Randy Harris and Chrysanne DiMarco. 2009. Constructing a Rhetorical Figuration Ontology. In Persuasive Technology and Digital Behaviour Intervention Symposium , pages 47-52, Edinburgh, Scotland.
- Helmut Schmid. 1994. Probabilistic Part-of-Speech Tagging Using Decision Trees. In Proceedings of International Conference on New Methods in Language Processing , pages 44-49, Manchester, Great Britain.
Cited by
Rhetorical Figure Detection: Chiasmus, Epanaphora, Epiphora
Dubremetz, M., & Nivre, J. (2018) · Frontiers in Digital Humanities · doi:10.3389/fdigh.2018.00010 · Cited by 27
“For instance, in a single book, there can be many thousands of candidates (Dubremetz and Nivre, 2015) for only one real chiasmus to be found.”
BackgroundSelf-citationLawrence, J. S., Visser, J., & Reed, C. (2017) · Argument & Computation · doi:10.3233/aac-170026 · Cited by 27
“The forms of schemes of structured repetition and (to a lesser extent) structured order should often be straightforward to identify automatically, which is why these figures were chosen in previous computational work as well [10,43].”
Rhetorical figures, arguments, computation
Harris, R. A., & Marco, C. D. (2017) · Argument & Computation · doi:10.3233/aac-170030 · Cited by 20
“Concerns about authenticity and design, however, lead many researchers to worry about false positives in figure detection [12,13,29,58].”
BackgroundInfluentialDecoding persuasion: a survey on ML and NLP methods for the study of online persuasion
Bassi, D., Fomsgaard, S. K., & Pereira-Fariña, M. (2024) · Frontiers in Communication · doi:10.3389/fcomm.2024.1457433 · Cited by 39
Ontological representations of rhetorical figures for argument mining
Mitrović, J., O’Reilly, C., Mladenović, M., & Handschuh, S. (2017) · Argument & Computation · doi:10.3233/aac-170027 · Cited by 20
“Research presented in [34,47,60] and [15] pointed out the importance of literary devices near to the candidate figure (called either features, constraints or markers) which indicate the presence of the figure.”
BackgroundMethodInfluential
Metadata
- Authors
- Dubremetz, M., & Nivre, J.
- Affiliations
- Uppsala University (SE)
- Venue
- Proceedings of the Fourth Workshop on Computational Linguistics for Literature
- Published
- 2015
- Pages
- 23-31
- OpenAlex
- W2250667488
- Semantic Scholar
- 9aa19627082e6139d8989300a445a1ca0c7b0bda
- Cited by
- 16
- References
- 15
- Citations by year
- 2024: 1 · 2023: 1 · 2021: 1 · 2020: 1 · 2018: 2 · 2017: 6 · 2016: 3 · 2015: 1
- FWCI
- 2.15
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL) (publishedVersion, cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Advanced Text Analysis Techniques
- Keywords
- chiasmus, rhetorical devices, word repetition, annotated corpus, information retrieval evaluation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-05, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-05 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Rhetorical Figure Detection: the Case of Chiasmus. https://app.cochat.ai/papers/10.3115/v1/w15-0703
- The paper
- Dubremetz, M., & Nivre, J. (2015). Rhetorical Figure Detection: the Case of Chiasmus. Proceedings of the Fourth Workshop on Computational Linguistics for Literature. https://doi.org/10.3115/v1/w15-0703
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.


