Simultaneous paraphrasing and translation by fine-tuning Transformer models
This work addresses a domain-specific challenge in language education, but it is incremental as it builds on existing pre-trained models and methods.
The paper tackled the problem of simultaneous translation and paraphrasing for language education by fine-tuning Transformer models, achieving a 27% absolute improvement in Weighted Macro F1 score for Hungarian and 33% for Portuguese compared to the baseline.
This paper describes the third place submission to the shared task on simultaneous translation and paraphrasing for language education at the 4th workshop on Neural Generation and Translation (WNGT) for ACL 2020. The final system leverages pre-trained translation models and uses a Transformer architecture combined with an oversampling strategy to achieve a competitive performance. This system significantly outperforms the baseline on Hungarian (27% absolute improvement in Weighted Macro F1 score) and Portuguese (33% absolute improvement) languages.