A User-Study on Online Adaptation of Neural Machine Translation to Human Post-Edits
This addresses the need for more efficient and higher-quality machine translation in interactive settings, particularly for patent translation, but is incremental as it extends prior simulation-based research to real user studies.
The study tackled the problem of interactive learning in neural machine translation by conducting the first user study on online adaptation to human post-edits in patent translation, resulting in a significant reduction in post-editing effort and improvements in translation quality metrics such as hTER, hBLEU, and BLEU/TER.
The advantages of neural machine translation (NMT) have been extensively validated for offline translation of several language pairs for different domains of spoken and written language. However, research on interactive learning of NMT by adaptation to human post-edits has so far been confined to simulation experiments. We present the first user study on online adaptation of NMT to user post-edits in the domain of patent translation. Our study involves 29 human subjects (translation students) whose post-editing effort and translation quality were measured on about 4,500 interactions of a human post-editor and a machine translation system integrating an online adaptive learning algorithm. Our experimental results show a significant reduction of human post-editing effort due to online adaptation in NMT according to several evaluation metrics, including hTER, hBLEU, and KSMR. Furthermore, we found significant improvements in BLEU/TER between NMT outputs and professional translations in granted patents, providing further evidence for the advantages of online adaptive NMT in an interactive setup.