Machine-assisted identification of rhyme in Russian verse

David J. Birnbaum

Files and directories

Code

Notebooks

(Most recent first)

• Extract and examine distances: Extract distance information from clustered object and look for cut-off
• Explore linkage and distance: Exploration and evaluation of linkage methods and distance metrics
• Samples notebook: dendrogram visualization of sample poems with different properties to explore behavior
• Progress report 4 notebook: at last some machine learning (clustering)!
• Progress report 3 notebook: decomposition into C(C) ~ V (replaces decomposition into syllable parts)
• Syllable decomposition scratchpad: scratch space for decomposition into syllables and into C(C) ~ V
• Progress report 2 notebook: decomposition into syllable parts (abandoned)
• Progress report 1 notebook: data preparation, syllabification

Library

• cyr2phon.py: Cyrillic to phonetic library; exposes cyr2phon.transliterate()
• utility.py: Utility functions; exposes utility.syllabify()

Development

• test_transliterate: Nose tests for transliteration code
• test_utility: Nose tests for utility code (syllabification)
• .travis.yml and requirements.txt: Configuration information for Travis CI

Data samples

• eo1.xml: First book of Aleksandr Puškin’s Eugene Onegin; see the Progress report for a description of the data source
• gippius_neljubov.xml: Zinaida Gippius, Neljubov (1907)
• brjusov_voron.xml Valerij Brjusov’s translation of Edgar Allan Poe’s “The raven” (1924)

Documentation

• project_plan.md: Original project proposal
• degrees-of-rhyme.md: Examples or types of imperfect rhyme, with discussion
• cluster-matching.md: Discussion of challenges in aligning heterosegmental consonant clusters
• progress_report.md: Progress report (last updated 2019-02-17)
• bibliography.md: Annotated bibliography

---

Acknowledgements

• This project is a contribution to Meter, rhythm, and rhyme: the computationally assisted analysis of formal features in Russian poetry, co-developed by David J. Birnbaum and Elise Thorsen. The content here builds on collaborative work from that larger project.
• Stanza markup in the Puškin corpus was implemented by Kyleen Pickering.
• Thanks to Na-Rae Han, Jevon Heath, Daniel Zheng, and members of the University of Pittsburgh Spring 2019 Linguistics 1340 course for comments and suggestions.