[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/papers/hbo-2020-schans-clustering-biblical-texts-using-recurrent/) [home](https://md.mova.elamur.ai/free/en/) / [docs](https://md.mova.elamur.ai/free/en/docs/) / [papers](https://md.mova.elamur.ai/free/en/docs/papers/) / [Ancient Hebrew](https://md.mova.elamur.ai/free/en/docs/papers/hbo/) / Clustering Biblical Texts Using Recurrent Neural Networks # Clustering Biblical Texts Using Recurrent Neural Networks **Authors:** Yanniek van der Schans, David Ruhe, [Wido van Peursen](https://md.mova.elamur.ai/free/en/docs/papers/authors/wido-van-peursen/), [Sandjai Bhulai](https://md.mova.elamur.ai/free/en/docs/papers/authors/sandjai-bhulai/) · **Year:** 2020 (Network Institute 2019) · **Venue:** Zenodo record 4003509 **Link:** [zenodo.org/records/4003509](https://zenodo.org/records/4003509) · **Licence:** [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) [**1** citations](https://openalex.org/works?filter=cites:W3112290764) openalex · 2026-10-18[**1** citations in our library](https://md.mova.elamur.ai/free/en/docs/papers/cited-by/hbo-2020-schans-clustering-biblical-texts-using-recurrent/) of the 140673 papers whose bibliographies we read[Zenodo (CERN European Organization for Nuclear Research)](https://openalex.org/S4306400562)[licence](https://creativecommons.org/licenses/by/4.0/) - [Publisher's page](https://doi.org/10.5281/zenodo.4003508) - [PDF](https://zenodo.org/records/4003509/files/Yanniek_David_FINAL.pdf) - [DOI 10.5281/zenodo.4003508](https://doi.org/10.5281/zenodo.4003508) - [OpenAlex](https://openalex.org/W3112290764) **Authors (4)** 1. [Yanniek van der Schans](https://openalex.org/A5007229379) h 1 · 1 citations · 1 works 2. [David Ruhe](https://openalex.org/A5071161029) [ORCID](https://orcid.org/0000-0003-2857-5255) · h 7 · 87 citations · 29 works 3. [Wido van Peursen](https://openalex.org/A5016185660) [ORCID](https://orcid.org/0000-0002-3142-5752) · h 9 · 290 citations · 204 works 4. [Sandjai Bhulai](https://openalex.org/A5026617038) [ORCID](https://orcid.org/0000-0003-1124-8821) · h 26 · 2300 citations · 249 works Citations and author metrics from openalex (2026-10-18); authors with the same name are not always told apart. ## What it is about The authors test the Early vs. Late Biblical Hebrew division (Genesis–Kings vs. Chronicles, Daniel, Ecclesiastes, Esther, Ezra–Nehemiah, Song of Songs) with LSTM language models trained on ETCBC data. Besides the words themselves they train on four annotation streams: verbal stem (binyan), clause type, phrase function and part of speech. For each book they average the hidden state over sampled passages and cluster the books with Ward's method. The verbal-stem stream separates the two groups most cleanly; the t-SNE plots agree with the literature that Hif'il is commoner early and Pi'el late. Song of Songs groups with Exodus and Leviticus, which the authors suspect is because all three are dominated by quoted speech. Their reading: the results lend some support to a diachronic division, with a middle group of books that moves between clusters. ## Ideas - I1. A transparent version without a neural net: per book (and per parasha) count the share of each binyan, of wayyiqtol clauses, and of each POS; cluster the five Torah books on these vectors and print the features that separate them. - I2. Control for speech: compute the same profiles separately for narrator and character voice (the `prag` voice column), since the paper's Song of Songs anomaly suggests that quoted speech, not period, can drive the clusters. - I3. Use Pi'el/Hif'il/Nif'al ratios as one of the stage markers in the comparison chapter, with Torah counts as the classical baseline. ## For Mova I1 and I3 are counts for [12. Biblical, Mishnaic and Modern Hebrew compared](https://md.mova.elamur.ai/free/en/docs/languages/hbo/12-biblical-mishnaic-modern/) and `06-verb.md` (binyanim) from the `macula` trees' FEATS; I2 uses `tools/macula/src/prag.rs` output to split by voice. All deterministic, so two runs must give identical tables. ## Cite The paper itself, not this card. BibTeX from the library's record of the work. [DOI 10.5281/zenodo.4003508](https://doi.org/10.5281/zenodo.4003508) ``` @inproceedings{schans2020clustering, title = {{Clustering Biblical Texts Using Recurrent Neural Networks}}, author = {Schans, Yanniek van der and Ruhe, David and Peursen, Wido van and Bhulai, Sandjai}, booktitle = {Zenodo (CERN European Organization for Nuclear Research)}, year = {2020}, doi = {10.5281/zenodo.4003508}, url = {https://doi.org/10.5281/zenodo.4003508} } ``` - [← previous Artificial intelligence based writer identification generates new evidence for the unknown scribes of the Dead Sea Scrolls exemplified by the Great Isaiah Scroll (1QIsaᵃ)](https://md.mova.elamur.ai/free/en/docs/papers/hbo-2020-popovic-artificial-intelligence-based-writer-identification/) - [next → Vom x-qatal zur Informationsstruktur – und retour. Bemerkungen zur Analyse althebräischer Sätze in der Poesie (From x-qatal to information structure – and back again)](https://md.mova.elamur.ai/free/en/docs/papers/hbo-2020-schiller-x-qatal-information-structure-back/) - [↑ back to Ancient Hebrew](https://md.mova.elamur.ai/free/en/docs/papers/hbo/) ## References 22 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Wilhelm Gesenius. 1815. Geschichte der hebräischen sprache und schrift: Eine philologisch-historisch einleitung in die sprachlehren und wörterbücher der hebräischen sprache. FCW Vogel. [find](https://scholar.google.com/scholar?q=Wilhelm+Gesenius%2E+1815%2E+Geschichte+der+hebr%C3%A4ischen+sprache+und+schrift%3A+Eine+philologisch%2Dhistorisch+einleitung+in+die+sprachlehren+und+w%C3%B6rterb%C3%BCcher+der+hebr%C3%A4ischen+sprache%2E+FCW+Vogel%2E) 2. Wilhelm Gesenius. 1902. Wilhelm Gesenius’ Hebräische Grammatik. Vol. 1. FCW vogel. [find](https://scholar.google.com/scholar?q=Wilhelm+Gesenius%2E+1902%2E+Wilhelm+Gesenius%E2%80%99+Hebr%C3%A4ische+Grammatik%2E+Vol%2E+1%2E+FCW+vogel%2E) 3. S. Hochreiter and J. Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735–1780. [find](https://scholar.google.com/scholar?q=S%2E+Hochreiter+and+J%2E+Schmidhuber%2E+1997%2E+Long+short%2Dterm+memory%2E+Neural+computation+9%2C+8+%281997%29%2C+1735%E2%80%931780%2E) 4. A. Hornkohl. 2017. All Is Not Lost: Linguistic Periodization in the Face of Textual and Literary Pluriformity. Advances in Biblical Hebrew Linguistics (2017), 53. [find](https://scholar.google.com/scholar?q=A%2E+Hornkohl%2E+2017%2E+All+Is+Not+Lost%3A+Linguistic+Periodization+in+the+Face+of+Textual+and+Literary+Pluriformity%2E+Advances+in+Biblical+Hebrew+Linguistics+%282017%29%2C+53%2E) 5. A. Hurvitz. 2000. Can Biblical Texts Be Dated Linguistically? Chronological Perspectives in the Historical Study of Biblical Hebrew. Lemaire, A. and M. Sæbo (eds.) Congress Volume, Oslo 1998 (2000). [find](https://scholar.google.com/scholar?q=A%2E+Hurvitz%2E+2000%2E+Can+Biblical+Texts+Be+Dated+Linguistically%3F+Chronological+Perspectives+in+the+Historical+Study+of+Biblical+Hebrew%2E+Lemaire%2C+A%2E+and+M%2E+S%C3%A6bo+%28eds%2E%29+Congress+Volume%2C+Oslo+1998+%282000%29%2E) 6. D. Kim. 2013. Early Biblical Hebrew, Late Biblical Hebrew, and linguistic variability: a sociolinguistic evaluation of the linguistic dating of biblical texts. Koninklijke Brill Nv. [find](https://scholar.google.com/scholar?q=D%2E+Kim%2E+2013%2E+Early+Biblical+Hebrew%2C+Late+Biblical+Hebrew%2C+and+linguistic+variability%3A+a+sociolinguistic+evaluation+of+the+linguistic+dating+of+biblical+texts%2E+Koninklijke+Brill+Nv%2E) 7. E.Y. Kutscher. 1982. A History of the Hebrew language. Magnes Press, The Hebrew University. [find](https://scholar.google.com/scholar?q=E%2EY%2E+Kutscher%2E+1982%2E+A+History+of+the+Hebrew+language%2E+Magnes+Press%2C+The+Hebrew+University%2E) 8. Wido van Peursen. 2019. A Computational Approach to Syntactic Diversity in the Hebrew Bible. Journal of Biblical Text Research 44 (2019), 237–253. [find](https://scholar.google.com/scholar?q=Wido+van+Peursen%2E+2019%2E+A+Computational+Approach+to+Syntactic+Diversity+in+the+Hebrew+Bible%2E+Journal+of+Biblical+Text+Research+44+%282019%29%2C+237%E2%80%93253%2E) 9. Wido van Peursen. 2019. Tracing Text Types in Biblical Hebrew. (2019). [find](https://scholar.google.com/scholar?q=Wido+van+Peursen%2E+2019%2E+Tracing+Text+Types+in+Biblical+Hebrew%2E+%282019%29%2E) [our card](https://md.mova.elamur.ai/free/en/docs/papers/hbo-2020-peursen-tracing-text-types-biblical-hebrew/) 10. R. Polzin. 1976. Late Biblical Hebrew: toward a historical typology of Biblical Hebrew prose. BRILL. [find](https://scholar.google.com/scholar?q=R%2E+Polzin%2E+1976%2E+Late+Biblical+Hebrew%3A+toward+a+historical+typology+of+Biblical+Hebrew+prose%2E+BRILL%2E) 11. Robert Rezetko and Ian Young. 2014. Historical linguistics and Biblical Hebrew: steps toward an integrated approach. Vol. 9. Society of Biblical Lit. [find](https://scholar.google.com/scholar?q=Robert+Rezetko+and+Ian+Young%2E+2014%2E+Historical+linguistics+and+Biblical+Hebrew%3A+steps+toward+an+integrated+approach%2E+Vol%2E+9%2E+Society+of+Biblical+Lit%2E) 12. M.F. Rooker. 1994. Diachronic Analysis and Features of Late Biblical Hebrew. Bulletin for Biblical research 4 (1994), 135–144. [find](https://scholar.google.com/scholar?q=M%2EF%2E+Rooker%2E+1994%2E+Diachronic+Analysis+and+Features+of+Late+Biblical+Hebrew%2E+Bulletin+for+Biblical+research+4+%281994%29%2C+135%E2%80%93144%2E) 13. D. Roorda. 2016. Text-Fabric. [find](https://scholar.google.com/scholar?q=D%2E+Roorda%2E+2016%2E+Text%2DFabric%2E) 14. D.J. Shepherd and C.J.H. Wright. 2018. Ezra and Nehemiah. Wm. B. Eerdmans Publishing. [find](https://scholar.google.com/scholar?q=D%2EJ%2E+Shepherd+and+C%2EJ%2EH%2E+Wright%2E+2018%2E+Ezra+and+Nehemiah%2E+Wm%2E+B%2E+Eerdmans+Publishing%2E) 15. E.P. van de Bijl, C. Kingham, W.T. van Peursen, and S. Bhulai. 2018. A Probabilistic Approach to Syntactic Variation in Biblical Hebrew. [find](https://scholar.google.com/scholar?q=E%2EP%2E+van+de+Bijl%2C+C%2E+Kingham%2C+W%2ET%2E+van+Peursen%2C+and+S%2E+Bhulai%2E+2018%2E+A+Probabilistic+Approach+to+Syntactic+Variation+in+Biblical+Hebrew%2E) [our card](https://md.mova.elamur.ai/free/en/docs/papers/hbo-2019-bijl-probabilistic-approach-syntactic-variation-biblical/) 16. L. van der Maaten and G. Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research 9 (2008), 2579–2605. [find](https://scholar.google.com/scholar?q=L%2E+van+der+Maaten+and+G%2E+Hinton%2E+2008%2E+Visualizing+data+using+t%2DSNE%2E+Journal+of+machine+learning+research+9+%282008%29%2C+2579%E2%80%932605%2E) 17. W.T. van Peursen and C. Kingham. 2018. The ETCBC Database of the Hebrew Bible. [find](https://scholar.google.com/scholar?q=W%2ET%2E+van+Peursen+and+C%2E+Kingham%2E+2018%2E+The+ETCBC+Database+of+the+Hebrew+Bible%2E) 18. A.J.C. Verheij. 2000. Bits, Bytes, and Binyanim. A Quantitative study of Verbal Lexeme Formations in the Hebrew Bible. Uitgeverij Peeters en Department Oosterse Studies Leuven. [find](https://scholar.google.com/scholar?q=A%2EJ%2EC%2E+Verheij%2E+2000%2E+Bits%2C+Bytes%2C+and+Binyanim%2E+A+Quantitative+study+of+Verbal+Lexeme+Formations+in+the+Hebrew+Bible%2E+Uitgeverij+Peeters+en+Department+Oosterse+Studies+Leuven%2E) 19. P.J. Werbos. 1990. Backpropagation through time: what it does and how to do it. Proc. IEEE 78, 10 (1990), 1550–1560. [find](https://scholar.google.com/scholar?q=P%2EJ%2E+Werbos%2E+1990%2E+Backpropagation+through+time%3A+what+it+does+and+how+to+do+it%2E+Proc%2E+IEEE+78%2C+10+%281990%29%2C+1550%E2%80%931560%2E) 20. I. Young. 2005. Biblical Texts Cannot Be Dated Linguistically. Hebrew Studies 46 (2005). [find](https://scholar.google.com/scholar?q=I%2E+Young%2E+2005%2E+Biblical+Texts+Cannot+Be+Dated+Linguistically%2E+Hebrew+Studies+46+%282005%29%2E) 21. Ian Young. 2017. Linguistic Dating of Biblical Texts: Volume 2. Routledge. [find](https://scholar.google.com/scholar?q=Ian+Young%2E+2017%2E+Linguistic+Dating+of+Biblical+Texts%3A+Volume+2%2E+Routledge%2E) 22. I. Young and R. Rezekto. 2008. Linguistic Dating of Biblical Texts: Volume 1. Routledge. [find](https://scholar.google.com/scholar?q=I%2E+Young+and+R%2E+Rezekto%2E+2008%2E+Linguistic+Dating+of+Biblical+Texts%3A+Volume+1%2E+Routledge%2E)