A Supervised Word Alignment Method based on Cross-Language Span Prediction using Multilingual BERT

no code implementations • EMNLP 2020 • Masaaki Nagata, Chousa Katsuki, Masaaki Nishino

For example, we achieved an F1 score of 86. 7 for the Chinese-English data, which is 13. 3 points higher than the previous state-of-the-art supervised methods.

Question Answering Sentence +1