# How effective is Multi-source pivoting for Translation of Low Resource Indian Languages?

arXiv: https://arxiv.org/abs/2406.13332 · HTML: https://mlsanity.com/paper/2406.13332/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 26 references that are in the map.
- First posted on arXiv 19 Jun 2024.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [On Layer Normalization in the Transformer Architecture](https://mlsanity.com/paper/2002.04745/) (2020)
- [Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges](https://mlsanity.com/paper/1907.05019/) (2019)
- [IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages](https://mlsanity.com/paper/2305.16307/) (2023)
- [Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation](https://mlsanity.com/paper/2011.00747/) (2020)
- [Zero-Resource Translation with Multi-Lingual Neural Machine Translation](https://mlsanity.com/paper/1606.04164/) (2016)
- [Attention Strategies for Multi-Source Sequence-to-Sequence Learning](https://mlsanity.com/paper/1704.06567/) (2017)
- [Unsupervised Multimodal Neural Machine Translation with Pseudo Visual Pivoting](https://mlsanity.com/paper/2005.03119/) (2020)
- [From Bilingual to Multilingual Neural Machine Translation by Incremental Training](https://mlsanity.com/paper/1907.00735/) (2019)
- [SamToNe: Improving Contrastive Loss for Dual Encoder Retrieval Models with Same Tower Negatives](https://mlsanity.com/paper/2306.02516/) (2023)
- [Multi-Source Neural Machine Translation with Missing Data](https://mlsanity.com/paper/1806.02525/) (2018)
- [Multi-Source Neural Machine Translation with Data Augmentation](https://mlsanity.com/paper/1810.06826/) (2018)
- [KazParC: Kazakh Parallel Corpus for Machine Translation](https://mlsanity.com/paper/2403.19399/) (2024)
- [Robustness of Multi-Source MT to Transcription Errors](https://mlsanity.com/paper/2305.16894/) (2023)

## Built on by (most cited first, 1 of 1)

- [Revisiting Multilingual Data Mixtures in Language Model Pretraining](https://mlsanity.com/paper/2510.25947/) (2025)

## Abstract (arXiv)

Machine Translation (MT) between linguistically dissimilar languages is challenging, especially due to the scarcity of parallel corpora. Prior works suggest that pivoting through a high-resource language can help translation into a related low-resource language. However, existing works tend to discard the source sentence when pivoting. Taking the case of English to Indian language MT, this paper explores the 'multi-source translation' approach with pivoting, using both source and pivot sentences to improve translation. We conducted extensive experiments with various multi-source techniques for translating English to Konkani, Manipuri, Sanskrit, and Bodo, using Hindi, Marathi, and Bengali as pivot languages. We find that multi-source pivoting yields marginal improvements over the state-of-the-art, contrary to previous claims, but these improvements can be enhanced with synthetic target language data. We believe multi-source pivoting is a promising direction for Low-resource translation.