Papers by Yukio Matsumura
Multimodal Machine Translation with Embedding Prediction (N19-3)
Copied to clipboard
| Challenge: | Pretrained word embeddings improve multimodal machine translation of low-resource domains due to a shortage of training data. |
| Approach: | They propose to combine pretrained word embeddings with search-based approaches to improve NMT of low-resource domains to better translate rare words. |
| Outcome: | The proposed approach improves translation performance by 1.24 METEOR and 2.49 BLEU and achieves 7.67 F-score. |
Graph-based Filtering of Out-of-Vocabulary Words for Encoder-Decoder Models (P18-3)
Copied to clipboard
| Challenge: | Encoder-decoder models employ words that are frequently used in the training corpus but may still include noisy words. |
| Approach: | They propose a method for selecting more suitable words for learning encoders by utilizing co-occurrence information. |
| Outcome: | The proposed method outperforms the baseline method in Japanese-to-English translation and grammatical error correction tasks with an F-measure of 1.48 points higher. |
Japanese Predicate Conjugation for Neural Machine Translation (N18-4)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) has a drawback in that it can generate only high-frequency words owing to the computational costs of the softmax function in the output layer. |
| Approach: | They propose two methods to generate low-frequency words and deal with unknown words using Japanese predicate conjugation information without discarding linguistic information. |
| Outcome: | The proposed methods can generate low-frequency words and deal with unknown words. |