# Pronoun-Targeted Fine-tuning for NMT with Hybrid Losses arXiv: https://arxiv.org/abs/2010.07638 ยท HTML: https://mlsanity.com/paper/2010.07638/ ## Key facts - Cited by 5 papers in the map (data through 14 Oct 2026). - First posted on arXiv 15 Oct 2020. ## Built on by (most cited first, 5 of 5) - [Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey](https://mlsanity.com/paper/2104.06951/) (2021) - [A baseline revisited: Pushing the limits of multi-segment models for context-aware translation](https://mlsanity.com/paper/2210.10906/) (2022) - [A Survey on Zero Pronoun Translation](https://mlsanity.com/paper/2305.10196/) (2023) - [You Are What You Train: Effects of Data Composition on Training Context-aware Machine Translation Models](https://mlsanity.com/paper/2509.14031/) (2025) - [Blur the Linguistic Boundary: Interpreting Chinese Buddhist Sutra in English via Neural Machine Translation](https://mlsanity.com/paper/2209.15164/) (2022) ## Abstract (arXiv) Popular Neural Machine Translation model training uses strategies like backtranslation to improve BLEU scores, requiring large amounts of additional data and training. We introduce a class of conditional generative-discriminative hybrid losses that we use to fine-tune a trained machine translation model. Through a combination of targeted fine-tuning objectives and intuitive re-use of the training data the model has failed to adequately learn from, we improve the model performance of both a sentence-level and a contextual model without using any additional data. We target the improvement of pronoun translations through our fine-tuning and evaluate our models on a pronoun benchmark testset. Our sentence-level model shows a 0.5 BLEU improvement on both the WMT14 and the IWSLT13 De-En testsets, while our contextual model achieves the best results, improving from 31.81 to 32 BLEU on WMT14 De-En testset, and from 32.10 to 33.13 on the IWSLT13 De-En testset, with corresponding improvements in pronoun translation. We further show the generalizability of our method by reproducing the improvements on two additional language pairs, Fr-En and Cs-En. Code available at .