mlsanityData to 14 Oct 2026

Introducing Rhetorical Parallelism Detection: A New Task with Datasets, Metrics, and Baselines

arXiv 2312.00100 ↗First posted 30 Nov 2023cs.CLcited by 7

Not on the map. Why?

Abstract (arXiv)

Rhetoric, both spoken and written, involves not only content but also style. One common stylistic tool is textitparallelism: the juxtaposition of phrases which have the same sequence of linguistic (textite.g., phonological, syntactic, semantic) features. Despite the ubiquity of parallelism, the field of natural language processing has seldom investigated it, missing a chance to better understand the nature of the structure, meaning, and intent that humans convey. To address this, we introduce the task of textitrhetorical parallelism detection. We construct a formal definition of it; we provide one new Latin dataset and one adapted Chinese dataset for it; we establish a family of metrics to evaluate performance on it; and, lastly, we create baseline systems and novel sequence labeling schemes to capture it. On our strictest metric, we attain F1 scores of 0.40 and 0.43 on our Latin and Chinese datasets, respectively.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 30 of its 91 references that are in the map. First posted on arXiv 30 Nov 2023.

Builds on

30 of 91 references.

References · 30

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  5. 2016Layer Normalizationcited by 5,669
  6. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  7. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  8. 2016Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translationcited by 1,475
  9. 2016Neural Architectures for Named Entity Recognitioncited by 550
  10. 2015Bidirectional LSTM-CRF Models for Sequence Taggingcited by 546
  11. 2016End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRFcited by 341
  12. 2019Learning Deep Transformer Models for Machine Translationcited by 309
18 more
  1. 2020Revisiting Pre-Trained Models for Chinese Natural Language Processingcited by 266
  2. 2019Transformers without Tears: Improving the Normalization of Self-Attentioncited by 153
  3. 2019BERT for Coreference Resolution: Baselines and Analysiscited by 125
  4. 2018On the Practical Computational Power of Finite Precision RNNs for Language Recognitioncited by 117
  5. 2018The Best of Both Worlds: Combining Recent Advances in Neural Machine Translationcited by 102
  6. 2018Tensor2Tensor for Neural Machine Translationcited by 85
  7. 2017Reporting Score Distributions Makes a Difference: Performance Study of LSTM-networks for Sequence Taggingcited by 73
  8. 2019Portuguese Named Entity Recognition using BERT-CRFcited by 73
  9. 2019LSTM Networks Can Perform Dynamic Countingcited by 45
  10. 2020Latin BERT: A Contextual Language Model for Classical Philologycited by 43
  11. 2016Disfluency Detection using a Bidirectional LSTMcited by 31
  12. 2018On Evaluating the Generalization of LSTM Models in Formal Languagescited by 17
  13. 2021Potential Idiomatic Expression (PIE)-English: Corpus for Classes of Idiomscited by 15
  14. 2019Giving Attention to the Unexpected: Using Prosody Innovations in Disfluency Detectioncited by 11
  15. 2020SGG: Spinbot, Grammarly and GloVe based Fake News Detectioncited by 8
  16. 2021Syllabic Quantity Patterns as Rhythmic Features for Latin Authorship Attributioncited by 5
  17. 2018"You are no Jack Kennedy": On Media Selection of Highlights from Presidential Debatescited by 3
  18. 2021Robust Learning for Text Classification with Multi-source Noise Simulation and Hard Example Miningcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 3.

7 papers.

  1. 2025SoftMatcha: A Soft and Fast Pattern Matcher for Billion-Scale Corpus Searchescited by 3
  2. 2025Quantitative Intertextuality from the Digital Humanities Perspective: A Surveycited by 2
  3. 2025Computational Discovery of Chiasmus in Ancient Religious Textcited by 0
  4. 2025Modeling Narrative Structure in Latin Epic Poetry with Automatically Generated Story Grammarscited by 0
  5. 2026Rewrite the News: Tracing Editorial Reuse Across News Agenciescited by 0
  6. 2026MiqraBERT: Regression-Based Sentence-BERT Finetuning for Biblical Hebrew Parallel Detectioncited by 0
  7. 2026Artificial Epanorthosis: Why large language models overuse a classical rhetorical figure, and how to mitigate itcited by 0