A Dataset of Mycenaean Linear B Sequences

Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), pages 2552–2561 Marseille, 11–16 May 2020 c⃝ European Language Resources Association (ELRA), licensed under CC-BY-NC 2552 A Dataset of Mycenaean Linear B Sequences K. Papavasileiou1, G. Owens2, D. Kosmopoulos3 1,3University of Patras GR-26504, Rio {1cpapavas, 3dkosmo}@upatras.gr 2Hellenic Mediterranean University GR-71410, Heraklion ogareth@hmu.gr Abstract We present our work towards a dataset of Mycenaean Linear B sequences gathered from the Mycenaean inscriptions written in the 13th and 14th century B.C. (c. 1400-1200 B.C.). The dataset contains sequences of Mycenaean words and ideograms according to the rules of the Mycenaean Greek language in the Late Bronze Age. Our ultimate goal is to contribute to the study, reading and understanding of ancient scripts and languages. Focusing on sequences, we seek to exploit the structure of the entire language, not just the Mycenaean vocabulary, to analyse sequential patterns. We use the dataset to experiment on estimating the missing symbols in damaged inscriptions. Keywords: Mycenaean Linear B script, sequential patterns 1. Introduction The Mycenaean script constitutes one of the writing systems used in the Aegean in the 2nd millennium B.C. Mycenaean Linear B, was a syllabic script deciphered by the English architect Michael Ventris in 1-6-1952, who proved that it expresses an archaic form of the Greek language. The Mycenaean Linear B texts, though they are brief and terse revealing little about structure, provide valuable information about unknown aspects of Mycenaean life. Despite the huge importance of the archaeological data, the written sources are those that highlight aspects of the political and social organization of the cultures under study, supporting the archaeological evidence with “historically” substantiated elements. For example, the decipherment of Mycenaean Linear B script added seven centuries to the history of the Hellenic language. Until then the oldest texts for the history of the Greek language were considered to be the Homeric epics. The Greek language is among the oldest languages and therefore a valuable tool for linguistic observation (Ruiperez & Melena, 1996). However, the importance of Mycenaean documents is remarkable, not only for linguistics and philology, but also for other sciences such as religious studies, ethnology, history and law, since from the Mycenaean texts is obtained information on the political and administrative organization, the social structure, the economic activity, the religion and the military aspect of the Mycenaean civilization. The computational methods are expected to offer a lot in decipherment tasks. Computational techniques (such as smoothed n-grams, Hidden Markov Models, Bayesian classifiers, Conditional Random Fields, etc.) might be applied to the problem of decipherment of ancient scripts (Knight & Yamada, 1999; Knight, et al., 2006; Ravi & Knight, 2008; Ravi & Knight, 2011b; Snyder, Barzilay, & Knight, 2010; Corlett & Penn, 2010; Nuhn, Mauser, & Ney, 2012; Nuhn & Ney, 2013) and also to the in-depth linguistic analysis (e.g., sentence detection, tokenization, lemmatization, part-of-speech tagging, etc.) of the already deciphered ones. The goal is not to replace the experts and their insight, but to contribute to their efforts by facilitating computational …

Content truncated to 500 words