Restoring and attributing ancient texts using deep neural networks

Y Assael, T Sommerschield, B Shillingford, M Bordbar… - Nature, 2022 - nature.com
Ancient history relies on disciplines such as epigraphy—the study of inscribed texts known
as inscriptions—for evidence of the thought, language, society and history of past …

Unleashing the potential of conversational AI: Amplifying Chat-GPT's capabilities and tackling technical hurdles

V Hassija, A Chakrabarti, A Singh, V Chamola… - IEEE …, 2023 - ieeexplore.ieee.org
Conversational AI has seen a growing interest among government, researchers, and
industrialists. This comprehensive survey paper provides an in-depth analysis of large …

[PDF][PDF] Machine learning for ancient languages: A survey

T Sommerschield, Y Assael, J Pavlopoulos… - Computational …, 2023 - direct.mit.edu
Ancient languages preserve the cultures and histories of the past. However, their study is
fraught with difficulties, and experts must tackle a range of challenging text-based tasks, from …

A survey on evaluation metrics for machine translation

S Lee, J Lee, H Moon, C Park, J Seo, S Eo, S Koo… - Mathematics, 2023 - mdpi.com
The success of Transformer architecture has seen increased interest in machine translation
(MT). The translation quality of neural network-based MT transcends that of translations …

A transformer-based neural machine translation model for Arabic dialects that utilizes subword units

LH Baniata, IKE Ampomah, S Park - Sensors, 2021 - mdpi.com
Languages that allow free word order, such as Arabic dialects, are of significant difficulty for
neural machine translation (NMT) because of many scarce words and the inefficiency of …

A study on performance improvement considering the balance between corpus in neural machine translation

C Park, K Park, H Moon, S Eo, H Lim - Journal of the Korea …, 2021 - koreascience.kr
Recent deep learning-based natural language processing studies are conducting research
to improve performance by training large amounts of data from various sources together …

HUE: Pretrained model and dataset for understanding Hanja documents of ancient Korea

H Yoo, J **, J Son, JY Bak, K Cho, A Oh - arxiv preprint arxiv:2210.05112, 2022 - arxiv.org
Historical records in Korea before the 20th century were primarily written in Hanja, an extinct
language based on Chinese characters and not understood by modern Korean or Chinese …

Time-aware ancient Chinese text translation and inference

E Chang, YT Shiue, HS Yeh, V Demberg - arxiv preprint arxiv:2107.03179, 2021 - arxiv.org
In this paper, we aim to address the challenges surrounding the translation of ancient
Chinese text:(1) The linguistic gap due to the difference in eras results in translations that …

Empirical analysis of parallel corpora and in-depth analysis using LIWC

C Park, M Shim, S Eo, S Lee, J Seo, H Moon, H Lim - Applied Sciences, 2022 - mdpi.com
The machine translation system aims to translate source language into target language.
Recent studies on MT systems mainly focus on neural machine translation. One factor that …

A generative model for the Mycenaean Linear B script and its application in infilling text from ancient tablets

K Papavassileiou, DI Kosmopoulos… - ACM Journal on …, 2023 - dl.acm.org
We present a generative neural language model for the most ancient proven stage of the
Greek language, the Mycenaean Greek attributed by the Linear B script. To capture the …