# Scalable Cross Lingual Pivots to Model Pronoun Gender for Translation

arXiv: https://arxiv.org/abs/2006.08881 · HTML: https://mlsanity.com/paper/2006.08881/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jun 2020.

## Built on by (most cited first, 4 of 4)

- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [GLaM: Efficient Scaling of Language Models with Mixture-of-Experts](https://mlsanity.com/paper/2112.06905/) (2021)
- [Evaluating and Improving the Coreference Capabilities of Machine Translation Models](https://mlsanity.com/paper/2302.08464/) (2023)
- [Model and Evaluation: Towards Fairness in Multilingual Text Classification](https://mlsanity.com/paper/2303.15697/) (2023)

## Abstract (arXiv)

Machine translation systems with inadequate document understanding can make errors when translating dropped or neutral pronouns into languages with gendered pronouns (e.g., English). Predicting the underlying gender of these pronouns is difficult since it is not marked textually and must instead be inferred from coreferent mentions in the context. We propose a novel cross-lingual pivoting technique for automatically producing high-quality gender labels, and show that this data can be used to fine-tune a BERT classifier with 92% F1 for Spanish dropped feminine pronouns, compared with 30-51% for neural machine translation models and 54-71% for a non-fine-tuned BERT model. We augment a neural machine translation model with labels from our classifier to improve pronoun translation, while still having parallelizable translation models that translate a sentence at a time.