Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

SumTablets: A Transliteration Dataset of Sumerian Tablets

Cole Simmons, Richard Diehl Martinez, Dan Jurafsky

TL;DR

The largest collection of Sumerian cuneiform tablets structured as Unicode glyph–transliteration pairs is presented, and a fine-tuned language model achieves an average transliteration character-level F-score of 97.55, demonstrating the potential use of deep learning methods in Assyriological research.

Abstract

Sumerian transliteration is a conventional system for representing a scholar's interpretation of a tablet in the Latin script. Thanks to visionary digital Assyriology projects such as ETCSL, CDLI, and Oracc, a large number of Sumerian transliterations have been published online, and these data are well-structured for a variety of search and analysis tasks. However, the absence of a comprehensive, accessible dataset pairing transliterations with a digital representation of the tablet's cuneiform glyphs has prevented the application of modern Natural Language Processing (NLP) methods to the task of Sumerian transliteration. To address this gap, we present SumTablets, a dataset pairing Unicode representations of 91,606 Sumerian cuneiform tablets (totaling 6,970,407 glyphs) with the associated transliterations published by Oracc. We construct SumTablets by first preprocessing and standardizing the Oracc transliterations before mapping each reading back to the Unicode representation of the source glyph. Further, we retain parallel structural information (e.g., surfaces, newlines, broken segments) through the use of special tokens. We release SumTablets as a Hugging Face Dataset (CC BY 4.0) and open source data preparation code via GitHub. Additionally, we leverage SumTablets to implement and evaluate two transliteration baselines: (1) weighted sampling from a glyph's possible readings, and (2) fine-tuning an autoregressive language model. Our fine-tuned language model achieves an average transliteration character-level F-score (chrF) of 97.55, demonstrating the immediate potential of transformer-based transliteration models in allowing experts to rapidly verify generated transliterations rather than manually transliterating tablets one-by-one.

SumTablets: A Transliteration Dataset of Sumerian Tablets

TL;DR

The largest collection of Sumerian cuneiform tablets structured as Unicode glyph–transliteration pairs is presented, and a fine-tuned language model achieves an average transliteration character-level F-score of 97.55, demonstrating the potential use of deep learning methods in Assyriological research.

Abstract

Sumerian transliteration is a conventional system for representing a scholar's interpretation of a tablet in the Latin script. Thanks to visionary digital Assyriology projects such as ETCSL, CDLI, and Oracc, a large number of Sumerian transliterations have been published online, and these data are well-structured for a variety of search and analysis tasks. However, the absence of a comprehensive, accessible dataset pairing transliterations with a digital representation of the tablet's cuneiform glyphs has prevented the application of modern Natural Language Processing (NLP) methods to the task of Sumerian transliteration. To address this gap, we present SumTablets, a dataset pairing Unicode representations of 91,606 Sumerian cuneiform tablets (totaling 6,970,407 glyphs) with the associated transliterations published by Oracc. We construct SumTablets by first preprocessing and standardizing the Oracc transliterations before mapping each reading back to the Unicode representation of the source glyph. Further, we retain parallel structural information (e.g., surfaces, newlines, broken segments) through the use of special tokens. We release SumTablets as a Hugging Face Dataset (CC BY 4.0) and open source data preparation code via GitHub. Additionally, we leverage SumTablets to implement and evaluate two transliteration baselines: (1) weighted sampling from a glyph's possible readings, and (2) fine-tuning an autoregressive language model. Our fine-tuned language model achieves an average transliteration character-level F-score (chrF) of 97.55, demonstrating the immediate potential of transformer-based transliteration models in allowing experts to rapidly verify generated transliterations rather than manually transliterating tablets one-by-one.
Paper Structure (17 sections, 1 equation, 3 figures, 4 tables)

This paper contains 17 sections, 1 equation, 3 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Creating SumTablets amphora
  4. Initial Data Cleaning
  5. Mapping transliterations to glpyhs
  6. Extra-semantic tokens
  7. Metadata
  8. Data Partitions
  9. Evaluating Transliteration Performance
  10. The Transliteration Task
  11. Dictionary Baseline
  12. Neural Baseline
  13. Analysis
  14. Limitations
  15. Dataset Limitations
  16. ...and 2 more sections

Figures (3)

  • Figure 1: An administrative Sumerian cuneiform tablet from Shuruppak, dated to the Early Dynastic IIIa period (ca. 2500 BCE). Cuneiform_Image_BM_15826
  • Figure 2: Illustration of the neural baseline model architecture. Inputs are read in as glyph tokens, while outputs are transliteration tokens.
  • Figure 3: The encoder model can produce a probability distribution over possible glyphs that can replace an <UNK> token. This is because the encoder is trained using an MLM objective.