# LogogramNLP: Comparing Visual and Textual Representations of Ancient Logographic Writing Systems for NLP

arXiv: https://arxiv.org/abs/2408.04628 · HTML: https://mlsanity.com/paper/2408.04628/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 53 references that are in the map.
- First posted on arXiv 8 Aug 2024.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [How multilingual is Multilingual BERT?](https://mlsanity.com/paper/1906.01502/) (2019)
- [ByT5: Towards a token-free future with pre-trained byte-to-byte models](https://mlsanity.com/paper/2105.13626/) (2021)
- [Deep Biaffine Attention for Neural Dependency Parsing](https://mlsanity.com/paper/1611.01734/) (2016)
- [How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models](https://mlsanity.com/paper/2012.15613/) (2020)
- [CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation](https://mlsanity.com/paper/2103.06874/) (2021)
- [When Being Unseen from mBERT is just the Beginning: Handling New Languages With Multilingual Language Models](https://mlsanity.com/paper/2010.12858/) (2020)
- [Extending Multilingual BERT to Low-Resource Languages](https://mlsanity.com/paper/2004.13640/) (2020)
- [CLIPPO: Image-and-Language Understanding from Pixels Only](https://mlsanity.com/paper/2212.08045/) (2022)
- [Latin BERT: A Contextual Language Model for Classical Philology](https://mlsanity.com/paper/2009.10053/) (2020)
- [Multilingual Pixel Representations for Translation and Effective Cross-lingual Transfer](https://mlsanity.com/paper/2305.14280/) (2023)
- [Finding structure in logographic writing with library learning](https://mlsanity.com/paper/2405.06906/) (2024)
- [Extending the Subwording Model of Multilingual Pretrained Models for New Languages](https://mlsanity.com/paper/2211.15965/) (2022)

## Built on by (most cited first, 6 of 6)

- [DongbaMIE: A Multimodal Information Extraction Dataset for Evaluating Semantic Understanding of Dongba Pictograms](https://mlsanity.com/paper/2503.03644/) (2025)
- [Translation or Recitation? Calibrating Evaluation Scores for Machine Translation of Extremely Low-Resource Languages](https://mlsanity.com/paper/2603.25222/) (2026)
- [Data Contamination in Neural Hieroglyphic Translation: A Reproducibility Study](https://mlsanity.com/paper/2605.07453/) (2026)
- [Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches](https://mlsanity.com/paper/2606.01145/) (2026)
- [One Image, No Tokens: A Controlled Study of Glyph-Based Chinese Language Modeling](https://mlsanity.com/paper/2607.03994/) (2026)
- [CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systems](https://mlsanity.com/paper/2609.22494/) (2026)

## Abstract (arXiv)

Standard natural language processing (NLP) pipelines operate on symbolic representations of language, which typically consist of sequences of discrete tokens. However, creating an analogous representation for ancient logographic writing systems is an extremely labor intensive process that requires expert knowledge. At present, a large portion of logographic data persists in a purely visual form due to the absence of transcription -- this issue poses a bottleneck for researchers seeking to apply NLP toolkits to study ancient logographic languages: most of the relevant data are images of writing. This paper investigates whether direct processing of visual representations of language offers a potential solution. We introduce LogogramNLP, the first benchmark enabling NLP analysis of ancient logographic languages, featuring both transcribed and visual datasets for four writing systems along with annotations for tasks like classification, translation, and parsing. Our experiments compare systems that employ recent visual and text encoding strategies as backbones. The results demonstrate that visual representations outperform textual representations for some investigated tasks, suggesting that visual processing pipelines may unlock a large amount of cultural heritage data of logographic languages for NLP-based analyses.