ABBIE: Attention-Based BI-Encoders for Predicting Where to Split Compound Sanskrit Words

Irfan Ali, Liliana Lo Presti, Igor Spano, Marco La Cascia

2025

Abstract

Sanskrit is a highly composite language, morphologically and phonetically complex. One of the major challenges in processing Sanskrit is the splitting of compound words that are merged phonetically. Recognizing the exact location of splits in a compound word is difficult since several possible splits can be found, but only a few of them are semantically meaningful. This paper proposes a novel deep learning method that uses two bi-encoders and a multi-head attention module to predict the valid split location in Sanskrit compound words. The two bi-encoders process the input sequence in direct and reverse order respectively. The model learns the character-level context in which the splitting occurs by exploiting the correlation between the direct and reverse dynamics of the characters sequence. The results of the proposed model are compared with a state-of-the-art technique that adopts a bidirectional recurrent network to solve the same task. Experimental results show that the proposed model correctly identifies where the compound word should be split into its components in 89.27% of cases, outperforming the state-of-the-art technique. The paper also proposes a dataset developed from the repository of the Digital Corpus of Sanskrit (DCS) and the University of Hyderabad (UoH) corpus.

Paper Citation

in Harvard Style

Ali I., Lo Presti L., Spano I. and La Cascia M. (2025). ABBIE: Attention-Based BI-Encoders for Predicting Where to Split Compound Sanskrit Words. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 334-344. DOI: 10.5220/0013155300003890

in Bibtex Style

@conference{icaart25,
author={Irfan Ali and Liliana Lo Presti and Igor Spano and Marco La Cascia},
title={ABBIE: Attention-Based BI-Encoders for Predicting Where to Split Compound Sanskrit Words},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART},
year={2025},
pages={334-344},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013155300003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART
TI - ABBIE: Attention-Based BI-Encoders for Predicting Where to Split Compound Sanskrit Words
SN - 978-989-758-737-5
AU - Ali I.
AU - Lo Presti L.
AU - Spano I.
AU - La Cascia M.
PY - 2025
SP - 334
EP - 344
DO - 10.5220/0013155300003890
PB - SciTePress