Neural Reranking Improves Subjective Quality of Machine Translation: NAIST at WAT2015

by   Graham Neubig, et al.
Nara Institute of Science and Technology

This year, the Nara Institute of Science and Technology (NAIST)'s submission to the 2015 Workshop on Asian Translation was based on syntax-based statistical machine translation, with the addition of a reranking component using neural attentional machine translation models. Experiments re-confirmed results from previous work stating that neural MT reranking provides a large gain in objective evaluation measures such as BLEU, and also confirmed for the first time that these results also carry over to manual evaluation. We further perform a detailed analysis of reasons for this increase, finding that the main contributions of the neural models lie in improvement of the grammatical correctness of the output, as opposed to improvements in lexical choice of content words.


page 1

page 2

page 3

page 4


Lexicons and Minimum Risk Training for Neural Machine Translation: NAIST-CMU at WAT2016

This year, the Nara Institute of Science and Technology (NAIST)/Carnegie...

Evaluating Machine Translation Performance on Chinese Idioms with a Blacklist Method

Idiom translation is a challenging problem in machine translation becaus...

Phrase Pair Mappings for Hindi-English Statistical Machine Translation

In this paper, we present our work on the creation of lexical resources ...

Grammar Accuracy Evaluation (GAE): Quantifiable Intrinsic Evaluation of Machine Translation Models

Intrinsic evaluation by humans for the performance of natural language g...

Improving Lexical Choice in Neural Machine Translation

We explore two solutions to the problem of mistranslating rare words in ...

Machine Translation Evaluation with Neural Networks

We present a framework for machine translation evaluation using neural n...

Please sign up or login with your details

Forgot password? Click here to reset