TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Machine Translation	Itihasa	Baseline (sn->en)	SacreBLEU	7.49	# 2
Machine Translation	Itihasa	Baseline (en->sn)	SacreBLEU	7.59	# 1

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/itihasa-a-large-scale-corpus-for-sanskrit-to/machine-translation-on-itihasa)](https://paperswithcode.com/sota/machine-translation-on-itihasa?p=itihasa-a-large-scale-corpus-for-sanskrit-to)`

Itihasa: A large-scale corpus for Sanskrit to English translation

ACL (WAT) 2021 · Rahul Aralikatte, Miryam de Lhoneux, Anoop Kunchukuttan, Anders Søgaard ·

This work introduces Itihasa, a large-scale translation dataset containing 93,000 pairs of Sanskrit shlokas and their English translations. The shlokas are extracted from two Indian epics viz., The Ramayana and The Mahabharata. We first describe the motivation behind the curation of such a dataset and follow up with empirical analysis to bring out its nuances. We then benchmark the performance of standard translation models on this corpus and show that even state-of-the-art transformer architectures perform poorly, emphasizing the complexity of the dataset.