---
title: "Deciphering Undersegmented Ancient Scripts Using — Luo 2021"
description: "The paper asks how to match an unsegmented or undersegmented script against the vocabulary of a known language when the language family of the lost script…"
authors: ["Jiaming Luo", "Frederik Hartmann", "Enrico Santus", "Regina Barzilay", "Yuan Cao"]
year: 2021
venue: "Transactions of the Association for Computational Linguistics"
source: "https://aclanthology.org/2021.tacl-1.5/"
doi: "10.1162/tacl_a_00354"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/tacl-2021-luo-deciphering-undersegmented-ancient-scripts-phonetic/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/tacl-2021-luo-deciphering-undersegmented-ancient-scripts-phonetic/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2021](https://md.research.elamur.ai/free/en/papers/2021/page/2/) / Deciphering Undersegmented Ancient Scripts Using Phonetic Prior

# Deciphering Undersegmented Ancient Scripts Using Phonetic Prior

**Authors:** [Jiaming Luo](https://md.research.elamur.ai/free/en/authors/jiaming-luo/); Frederik Hartmann; [Enrico Santus](https://md.research.elamur.ai/free/en/authors/enrico-santus/); [Regina Barzilay](https://md.research.elamur.ai/free/en/authors/regina-barzilay/); [Yuan Cao](https://md.research.elamur.ai/free/en/authors/yuan-cao/) · **Year:** 2021 · **Venue:** Transactions of the Association for Computational Linguistics, vol. 9, pp. 69–81 **Link:** [aclanthology.org/2021.tacl-1.5](https://aclanthology.org/2021.tacl-1.5/) · library `tacl-2021-luo-deciphering-undersegmented-ancient-scripts-phonetic` · **Licence:** [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) (ACL Anthology)

[**20** citations](https://openalex.org/works?filter=cites:W3129293584) OpenAlex · 2026-10-14 · [**9** citations in our library](https://md.research.elamur.ai/free/en/papers/tacl-2021-luo-deciphering-undersegmented-ancient-scripts-phonetic/cited-by/) of the 140673 papers whose bibliographies we read · [Transactions of the Association for Computational Linguistics](https://aclanthology.org/volumes/2021.tacl-1/) · [licence](https://creativecommons.org/licenses/by/4.0/)

- [Publisher's page](https://aclanthology.org/2021.tacl-1.5/)
- [PDF](https://aclanthology.org/2021.tacl-1.5.pdf)
- [DOI 10.1162/tacl_a_00354](https://doi.org/10.1162/tacl_a_00354)
- [OpenAlex](https://openalex.org/W3129293584)

**Authors (5)**

1. [Jiaming Luo](https://openalex.org/A5029740891) [Semantic Scholar](https://www.semanticscholar.org/author/19236313) · h 4 · 74 citations · 8 works
2. [Frederik Hartmann](https://openalex.org/A5003018532) [ORCID](https://orcid.org/0000-0002-6649-5371) · [Semantic Scholar](https://www.semanticscholar.org/author/46486499) · h 6 · 98 citations · 30 works
3. [Enrico Santus](https://openalex.org/A5059288410) [ORCID](https://orcid.org/0000-0002-7327-2731) · [Semantic Scholar](https://www.semanticscholar.org/author/150991377) · h 21 · 1507 citations · 100 works
4. [Regina Barzilay](https://openalex.org/A5010124873) [ORCID](https://orcid.org/0000-0002-2921-8201) · [Semantic Scholar](https://www.semanticscholar.org/author/1741283) · h 91 · 34823 citations · 358 works
5. [Yuan Cao](https://openalex.org/A5101989491) [ORCID](https://orcid.org/0000-0002-2495-4701) · [Semantic Scholar](https://www.semanticscholar.org/author/145144022) · h 28 · 9158 citations · 84 works

Citations and author metrics: OpenAlex, 2026-10-14; authors with the same name are not always told apart.

## What it is about

The paper asks how to match an unsegmented or undersegmented script against the vocabulary of a known language when the language family of the lost script is not known. The model jointly segments the text and aligns each matched span to a known stem with a monotonic, edit-distance-style alignment. Characters are embedded from their IPA features, so that similar sounds get similar vectors, and a penalty keeps the lost script from losing sounds (each lost symbol should map to one known sound). It also proposes a closeness measure: coverage of the lost text against a known language's vocabulary, plotted against confidence. On deciphered test cases the full model scores A@10 of 0.661 averaged over settings for Gothic (0.419 with no phonological knowledge), and it finds Proto-Germanic as the closest known language, with 75 percent A@10 even with no prior knowledge. On Iberian personal names it reaches 75 percent top-10 with full knowledge; the closeness measure does not single out Basque.

## Ideas

- I1. Closeness by coverage: for a text in one Aramaic variety, match its words against each other variety's stem list and plot coverage against match confidence. This gives an empirical test of which variety (`languages/arc-x-targum`, `languages/tmr`, `languages/jpa`) is nearest, and it can be checked against the known history.
- I2. Monotonic alignment with insertion penalty: align consonant skeletons of cognate forms with substitution, deletion and insertion costs, where insertion is penalised by a parameter alpha. Use it to match a word in one variety with its counterpart in another, and as a distance for `tools/ocrfix` repairs.
- I3. Sound-inventory check: require each consonant of a variety to correspond to a consistent consonant of the known language, and flag the cases where one letter maps to several sounds or where a sound disappears. Write the resulting table into [languages/arc/script-phonology.md](https://mova.elamur.ai/free/en/docs/languages/arc/script-phonology/).

## For Mova

I1 belongs in [languages/arc/family.md](https://mova.elamur.ai/free/en/docs/languages/arc/family/) and in the closeness tests for the Aramaic varieties. I2 is an alignment routine for `tools/ocrfix` and for cognate lookup across `languages/arc`. I3 is a check for [languages/arc/script-phonology.md](https://mova.elamur.ai/free/en/docs/languages/arc/script-phonology/). The decipherment goal itself is outside Mova; the parts that transfer are the alignment, the closeness measure and the inventory check.

## Cite

The paper itself, not this card. BibTeX from the library's record of the work. [DOI 10.1162/tacl_a_00354](https://doi.org/10.1162/tacl_a_00354)

```bibtex
@article{luo2021deciphering,
  title = {{Deciphering Undersegmented Ancient Scripts Using Phonetic Prior}},
  author = {Luo, Jiaming and Hartmann, Frederik and Santus, Enrico and Barzilay, Regina and Cao, Yuan},
  journal = {Transactions of the Association for Computational Linguistics},
  year = {2021},
  doi = {10.1162/tacl\_a\_00354},
  url = {https://doi.org/10.1162/tacl_a_00354}
}
```

- [← previous Debiasing Pre-trained Contextualised Embeddings](https://md.research.elamur.ai/free/en/papers/kaneko-2021-debiasing-pre-trained-contextualised-embeddings/)
- [next → DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations](https://md.research.elamur.ai/free/en/papers/giorgi-2021-declutr-deep-contrastive-learning-unsupervised/)
- [↑ back to papers of 2021](https://md.research.elamur.ai/free/en/papers/2021/page/2/)

## References

16 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Eduardo Orduña Aznar. 2005. Sobre algunos posibles numerales en textos ibéricos. Palaeohispanica, 5:491–506. [find](https://scholar.google.com/scholar?q=Eduardo+Ordun%CC%83a+Aznar%2E+2005%2E+Sobre+algunos+posibles+numerales+en+textos+ibe%CC%81ricos%2E+Palaeohispanica%2C+5%3A491%E2%80%93506%2E)
2. Taylor Berg-Kirkpatrick and Dan Klein. 2013. Decipherment with a million random restarts. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 874–878. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Taylor+Berg%2DKirkpatrick+and+Dan+Klein%2E+2013%2E+Decipherment+with+a+million+random+restarts%2E+In+Proceedings+of+the+2013+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+pages+874%E2%80%93878%2E+Asso)
3. Kevin Knight and Kenji Yamada. 1999. A computational approach to deciphering unknown scripts. Unsupervised Learning in Natural Language Processing. [find](https://scholar.google.com/scholar?q=Kevin+Knight+and+Kenji+Yamada%2E+1999%2E+A+computational+approach+to+deciphering+unknown+scripts%2E+Unsupervised+Learning+in+Natural+Language+Processing%2E)
4. Guillaume Lample, Alexis Conneau, Ludovic Denoyer, and Marc’Aurelio Ranzato. 2018a. Unsupervised machine translation using monolingual corpora only. [↗](https://doi.org/10.48550/arxiv.1711.00043) [our card](https://md.research.elamur.ai/free/en/papers/lample-2017-unsupervised-machine-translation-using-monolingual/)
5. Donald A. Ringe. 2017. From Proto-Indo-European to Proto-Germanic. Oxford. [↗](https://doi.org/10.1093/oso/9780198792581.001.0001)
6. Alejandro Garcia Sinner and Javier Velaza. 2019. Palaeohispanic Languages and Epigraphies. Oxford University Press. [find](https://scholar.google.com/scholar?q=Alejandro+Garcia+Sinner+and+Javier+Velaza%2E+2019%2E+Palaeohispanic+Languages+and+Epigraphies%2E+Oxford+University+Press%2E)
7. Guillaume Lample, Alexis Conneau, Marc’Aurelio Ranzato, Ludovic Denoyer, and Hervé Jégou. 2018b. Word translation without parallel data. In International Conference on Learning Representations. [↗](https://doi.org/10.48550/arxiv.1710.04087)
8. Benjamin Snyder, Regina Barzilay, and Kevin Knight. 2010. A statistical model for lost language decipherment. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pages 1048–1057, Uppsala, Sweden. Association for Computational Linguistics. DOI: https://doi.org/10.1093/oso/9780198792581.001.0001 [↗](https://doi.org/10.1093/oso/9780198792581.001.0001)
9. Jiaming Luo, Yuan Cao, and Regina Barzilay. 2019. Neural decipherment via minimum-cost flow: From ugaritic to linear b. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3146–3155, Florence, Italy. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Jiaming+Luo%2C+Yuan+Cao%2C+and+Regina+Barzilay%2E+2019%2E+Neural+decipherment+via+minimum%2Dcost+flow%3A+From+ugaritic+to+linear+b%2E+In+Proceedings+of+the+57th+Annual+Meeting+of+the+Association+for+Computational+L) [our card](https://md.research.elamur.ai/free/en/papers/acl-2019-luo-neural-decipherment-minimum-cost-flow/)
10. Kenneth N. Stevens. 2000. Acoustic phonetics, volume 30. MIT Press. [find](https://scholar.google.com/scholar?q=Kenneth+N%2E+Stevens%2E+2000%2E+Acoustic+phonetics%2C+volume+30%2E+MIT+Press%2E)
11. Noemı́ Moncunill Martı́ and others. 2017. Indigenous naming practices in the western Mediterranean: The case of Iberian. Studia Antiqua et Archaeologica, 23(1):7–20. [find](https://scholar.google.com/scholar?q=Noem%C4%B1%CC%81+Moncunill+Mart%C4%B1%CC%81+and+others%2E+2017%2E+Indigenous+naming+practices+in+the+western+Mediterranean%3A+The+case+of+Iberian%2E+Studia+Antiqua+et+Archaeologica%2C+23%281%29%3A7%E2%80%9320%2E)
12. Larry Trask. 2008. Etymological Dictionary of Basque. [http://www.bulgari-istoria](http://www.bulgari-istoria) -2010.com/Rechnici/baski-rechnik .pdf. [↗](http://www.bulgari-istoria)
13. David R. Mortensen, Siddharth Dalmia, and Patrick Littell. 2018. Epitran: Precision G2P for many languages. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Paris, France. European Language Resources Association (ELRA). [find](https://scholar.google.com/scholar?q=David+R%2E+Mortensen%2C+Siddharth+Dalmia%2C+and+Patrick+Littell%2E+2018%2E+Epitran%3A+Precision+G2P+for+many+languages%2E+In+Proceedings+of+the+Eleventh+International+Conference+on+Language+Resources+and+Evaluation) [our card](https://md.research.elamur.ai/free/en/papers/mortensen-2018-epitran-precision-g2p-many-languages/)
14. Norbert Wagner. 2006. Zu got. hv, q und ai, au. Historische Sprachforschung/Historical Linguistics, pages 286–291. [find](https://scholar.google.com/scholar?q=Norbert+Wagner%2E+2006%2E+Zu+got%2E+hv%2C+q+und+ai%2C+au%2E+Historische+Sprachforschung%2FHistorical+Linguistics%2C+pages+286%E2%80%93291%2E)
15. Julius Zacher. 1855. Das Gothische Alphabet Vulfilas und das Runen Alphabet: eine Sprachwissenschaftliche Untersuchung, FA Brockhaus. [find](https://scholar.google.com/scholar?q=Julius+Zacher%2E+1855%2E+Das+Gothische+Alphabet+Vulfilas+und+das+Runen+Alphabet%3A+eine+Sprachwissenschaftliche+Untersuchung%2C+FA+Brockhaus%2E)
16. Malte Nuhn, Julian Schamper, and Hermann Ney. 2013. Beam search for solving substitution ciphers. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1568–1576, Sofia, Bulgaria. Association for Computational Linguistics. A Appendices A.1 Derivations for Dynamic Programming [find](https://scholar.google.com/scholar?q=Malte+Nuhn%2C+Julian+Schamper%2C+and+Hermann+Ney%2E+2013%2E+Beam+search+for+solving+substitution+ciphers%2E+In+Proceedings+of+the+51st+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28Volume+1%3A+)