Search Results for author:
Found 7 papers, 3 papers with code
Filtering Pseudo-References by Paraphrasing for Automatic Evaluation of Machine Translation
We use the outputs of off-the-shelf MT systems as pseudo-references filtered by paraphrasing in addition to a single human reference (gold reference).
Multimodal Machine Translation with Embedding Prediction
Multimodal machine translation is an attractive application of neural machine translation (NMT).
Graph-based Filtering of Out-of-Vocabulary Words for Encoder-Decoder Models
For Japanese-to-English translation, this method achieves a BLEU score that is 0. 56 points more than that of a baseline.
Japanese Predicate Conjugation for Neural Machine Translation
Neural machine translation (NMT) has a drawback in that can generate only high-frequency words owing to the computational costs of the softmax function in the output layer.
Tokyo Metropolitan University Neural Machine Translation System for WAT 2017
We implemented beam search and ensemble decoding in the NMT system.
English-Japanese Neural Machine Translation with Encoder-Decoder-Reconstructor
We confirm that our re-implementation also shows the same tendency and alleviates the problem of repeating and missing words in the translation on a English-Japanese task too.
