No CrossRef data available.
Article contents
GREEK, LATIN AND AUGMENTED INTELLIGENCE: THE OTHER AI
Published online by Cambridge University Press: 26 February 2025
Abstract
An abstract is not available for this content so a preview has been provided. Please use the Get access link above for information on how to access this content.
- Type
- Subject Profile
- Information
- Copyright
- Copyright © The Author(s), 2025. Published by Cambridge University Press on behalf of The Classical Association
References
1 For a description of the need for treebanks, see G. Crane, ‘Don't miss the lexicographers for the treebanks Philology in an electronic age’, Conference on the Cambridge Greek Lexicon (2002), https://www.academia.edu/82054421/Dont_miss_the_lexicographers_for_the_treebanks_Philology_in_an_electronic_age. Five years later, in 2007, D. Bamman would begin working on alignments of Greek and Latin with English translations. The following year, 2008, H. Diakoff of the Alpheios Project recognised the value of manually aligning source texts and translations. Diakoff led development of a manual translation alignment editor.
2 For translation alignment see C. Palladino and T. Yousef, ‘To say almost the same thing? A study on cross-linguistic variation in ancient texts and their translations’, Digital Scholarship in the Humanities 38 (2023), 1200–13, https://doi.org/10.1093/llc/fqac086; M. Alharbi et al., ‘TransVis: Integrated Distant and Close Reading of Othello Translations’, IEEE Transactions on Visualization and Computer Graphics 28 (2022), 1397–414, https://doi.org/10.1109/TVCG.2020.3012778; A. Fraisse, ‘A Multilingual Dashboard to Analyse Intercultural Knowledge Circulation’, in: O. Alonso et al. (edd.), Linking Theory and Practice of Digital Libraries (2023), pp. 8–14, https://doi.org/10.1007/978-3-031-43849-3_2; and for recent work with treebanks see J. Kostkan et al., ‘OdyCy – A general-purpose NLP pipeline for Ancient Greek’, in: S. Degaetano-Ortlieb et al. (edd.), Proceedings of the 7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (2023), pp. 128–34, https://aclanthology.org/2023.latechclfl-1.14; F. Gamba and D. Zeman, ‘Universalising Latin Universal Dependencies: A Harmonisation of Latin Treebanks in UD’, in: L. Grobol and F. Tyers (edd.), Proceedings of the Sixth Workshop on Universal Dependencies (UDW, GURT/SyntaxFest 2023) (2023), pp. 7–16, https://aclanthology.org/2023.udw-1.2.
3 For one example of the use of machine learning in classical philology see B. Graziosi et al., ‘Machine Learning and the Future of Philology: A Case Study’, TAPA 153 (2023), 253–84, https://doi.org/10.1353/apa.2023.a901022.
4 For more on a definition of augmented intelligence (first defined by D.C. Engelbart in 1962) see D.C. Engelbart, ‘Augmenting Human Intellect: A Conceptual Framework’, in D. Araya and P. Marber (edd.), Augmented Education in the Global Age (2023), pp. 13–29, https://doi.org/10.4324/9781003230762; M. Pasquinelli, ‘Augmented Intelligence’, Critical Keywords for the Digital Humanities (2014), https://matteopasquinelli.com/augmented-intelligence/; M.N.O. Sadiku and S.M. Musa, ‘Augmented Intelligence’, in: M.N.O. Sadiku and S.M. Musa, A Primer on Multiple Intelligences (2021), pp. 191–9.
5 The Center for Hellenic Studies Homeric Iliad: https://chs.harvard.edu/primary-source/homeric-iliad-sb/.
6 The alignments were manually produced as a part of M. Foradi, ‘Engagement with Classical Literature in the Framework of a Citizen Science Project Using Translation Alignment: Data Accuracy and Pedagogical Effectiveness’ (Diss., Leipzig University, 2020). The figure was taken from the initial version of Beyond Translation, https://beyond-translation.perseus.org. The translation is from H.W. Clarke, The Divan by Hafez: Translated for the First Time out of the Persian into English Prose (1891), https://archive.org/details/thedivan01hafiuoft.
7 For example, P.F. Brown et al., ‘The Mathematics of Statistical Machine Translation: Parameter Estimation’, Computational Linguistics 19 (1993), 263–311; F. Smadja et al., ‘Translating Collocations for Bilingual Lexicons: A Statistical Approach’, Computational Linguistics 22 (1996), 1–38.
8 See D. Bamman and G. Crane, ‘Measuring historical word sense variation’, Proceedings of the 11th Annual International ACM/IEEE Joint Conference on Digital Libraries (2011), pp. 1–10, https://doi.org/10.1145/1998076.1998078, Figure 5.
9 Foradi (n. 6) discusses the earliest version of the Alpheios alignment editor at length. For the most recent version of the Alpheios Alignment editor see https://alignment.alpheios.net/whats-new.html; https://www.youtube.com/watch?v=AJwd_JXLL5Q.
11 T. Yousef et al., ‘An automatic model and Gold Standard for translation alignment of Ancient Greek’, in: N. Calzolari et al. (edd.), Proceedings of the Thirteenth Language Resources and Evaluation Conference (2022), pp. 5894–905, https://aclanthology.org/2022.lrec-1.634, and C. Palladino et al., ‘Translation Alignment for Ancient Greek: Annotation Guidelines and Gold Standards’, Journal of Open Humanities Data 9 (2023), https://doi.org/10.5334/johd.131.
12 T. Yousef et al., ‘Automatic Translation Alignment for Ancient Greek and Latin’, in: R. Sprugnoli et al. (edd.), Proceedings of the Second Workshop on Language Technologies for Historical and Ancient Languages (2022), pp. 101–7, https://aclanthology.org/2022.lt4hala-1.14.
13 In information retrieval these figures would be described as precision (91.5% of the retrieved items were correct) and recall (87.3% of the correct items were found).
15 C. Palladino, ‘Reading Texts in Digital Environments: Applications of Translation Alignment for Classical Language Learning’, The Journal of Interactive Technology and Pedagogy 18 (2020), https://cuny.manifoldapp.org/read/reading-texts-in-digital-environments-applications-of-translation-alignment-for-classical-language-learning-310daf57-ed21-4150-b5ba-7386399ef905/section/5ae515f9-4e47-4a1e-a0c6-eb3b5f0b1a03.
16 F. Shamsian and G. Crane, ‘Open Resources for Corpus-Based Learning of Ancient Greek in Persian’, Journal of Interactive Technology and Pedagogy 21 (2021), https://cuny.manifoldapp.org/read/open-resources-for-corpus-based-learning-of-ancient-greek-in-persian/section/2a96a89e-a4f8-4d47-bf78-f1d9a5b671bd.
17 J. Hilleary, ‘Facilitating Language Hacking with Digital Tools: A Study of Translation Alignment’ (Tufts University, Msc in Computer Science, 2024).
18 Examples of research using treebank data include Bamman et al., ‘A Case Study in Treebank Collaboration and Comparison: Accusativus Cum Infinitivo and Subordination in Latin’, Prague Bulletin of Mathematical Linguistics 90 (2008), 109–22; D. Bamman and G. Crane (n. 8); G.G.A. Celano and G. Crane, ‘Semantic Role Annotation in the Ancient Greek Dependency Treebank’, in: M. Dickinson et al. (edd.), Proceedings of the Fourteenth International Workshop on Treebanks and Linguistic Theories (TLT14) (2015), pp. 26–34; G.G.A. Celano, ‘An Automatic Morphological Annotation and Lemmatization for the IDP Papyri’, in: N. Reggiani (ed.), Digital Papyrology II (2018), pp. 139–48, https://doi.org/10.1515/9783110547450-008; G.G.A. Celano, ‘The Dependency Treebanks for Ancient Greek and Latin’, in: M. Berti (ed.), Digital Classical Philology (2019), pp. 279–98, https://doi.org/10.1515/9783110599572-016; G.G.A. Celano, ‘Lemmatization and morphological analysis for the Latin Dependency Treebank’, Studi e Saggi Linguistici 58 (2020), 21–38; R. Gorman, ‘Author Identification of Short Texts Using Dependency Treebanks without Vocabulary’, Digital Scholarship in the Humanities 35 (2020), 812–25, https://doi.org/10.1093/llc/fqz070; R. Gorman, ‘Universal Dependencies and Author Attribution of Short Texts with Syntax Alone’, Digital Humanities Quarterly 16 (2022), http://www.digitalhumanities.org/dhq/vol/16/2/000606/000606.html; F. Mambrini and M. Passarotti, ‘Non-Projectivity in the Ancient Greek Dependency Treebank’, Proceedings of the Second International Conference on Dependency Linguistics (DepLing 2013) (2013), pp. 177–86, https://aclanthology.org/W13-3720; F. Mambrini and M. Passarotti, ‘Subject-Verb Agreement with Coordinated Subjects in Ancient Greek: A Treebank-Based Study’, Journal of Greek Linguistics 16 (2016), 87–116, https://doi.org/10.1163/15699846-01601003; F. Mambrini and M. Passarotti, ‘Linked Open Treebanks. Interlinking Syntactically Annotated Corpora in the LiLa Knowledge Base of Linguistic Resources for Latin’, in: M. Candito et al. (edd.), Proceedings of the 18th International Workshop on Treebanks and Linguistic Theories (TLT, SyntaxFest 2019) (2019), pp. 74–81, https://aclanthology.org/W19-7808/; F. Mambrini, ‘Treebanking in the World of Thucydides. Linguistic Annotation for the Hellespont Project’, Digital Humanities Quarterly 10 (2016), http://www.digitalhumanities.org/dhq/vol/10/2/000251/000251.html; F. Mambrini, ‘Nominal vs copular clauses in a diachronic corpus of Ancient Greek historians’, Journal of Greek Linguistics 19 (2019), 90–113; T. Van Hal and A. Keersmaekers, ‘Visualizing the Ancient Greek Forest through the Trees: How Treebanks Can Advance the Education of Classical Languages’, Les Études Classiques 89 (2021), 349–72; M. Vierros and E. Henriksson, ‘PapyGreek Treebanks: A Dataset of Linguistically Annotated Greek Documentary Papyri’, Journal of Open Humanities Data 7 (2021), 26, https://doi.org/10.5334/johd.55.
21 Crane (n. 1).
22 National Science Foundation (BCS-0616521).
25 See D. Bamman et al. (n. 18).
27 For an overview of much of this work as well as some later work see G.G.A. Celano (n. 18 [2019]); for a discussion of the challenges involved in integrating data from different treebanks see B. Hwang, ‘Experiments in Digital Philology’, Perseus Journal of Data Preservation and Sustainability (2023), https://pdldatajournal.pubpub.org/pub/article2.
28 A. Keersmaekers, ‘The GLAUx corpus: methodological issues in designing a long-term, diverse, multi-layered corpus of Ancient Greek’, in: N. Tahmasebi et al. (edd.), Proceedings of the 2nd International Workshop on Computational Approaches to Historical Language Change 2021 (2021), pp. 39–50, https://doi.org/10.18653/v1/2021.lchange-1.6; https://github.com/alekkeersmaekers/GLAUx.
29 R. McDonald et al., ‘Universal Dependency Annotation for Multilingual Parsing’, Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) (2013), pp. 92–7, https://aclanthology.org/P13-2017; https://universaldependencies.org/.
31 See P.J. Burns, ‘LatinCy: Synthetic Trained Pipelines for Latin NLP’, arXiv:2305.04365 (2023), https://doi.org/10.48550/arXiv.2305.04365.
32 These figures originally appeared as Table 9 and Figure 4 in D. Bamman and G. Crane, ‘Building a dynamic lexicon from a digital library’, Proceedings of the 8th ACM/IEEE-CS Joint Conference on Digital Libraries (2008), pp. 11–20, https://doi.org/10.1145/1378889.1378892.
33 The National Endowment for the Humanities funded the project ‘The Dynamic Lexicon: Cyberinfrastructure and the automatic analysis of historical languages’, PR-50013-08: 2007–2012.