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 finetune a trained machine translation model. Through a combination of targeted finetuning 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 simple contextual model without using any additional data. We target the improvement of pronoun translations through our finetuning 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 simple 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.

@inproceedings{jwala-et-al-emnlp-20, abstract = {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 finetune a trained machine translation model. Through a combination of targeted finetuning 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 simple contextual model without using any additional data. We target the improvement of pronoun translations through our finetuning 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 simple 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.}, address = {Punta Cana, Dominican Republic}, author = {Prathyusha Jwalapuram and Shafiq Joty and Youlin Shen}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing}, numpages = {9}, pages = {2267–2279}, publisher = {ACL}, series = {EMNLP'20}, title = {Pronoun-Targeted Finetuning for NMT with Hybrid Losses}, url = {https://www.aclweb.org/anthology/2020.emnlp-main.177/}, year = {2020} }