Modeling Voting for System Combination in Machine Translation

by   Xuancheng Huang, et al.

System combination is an important technique for combining the hypotheses of different machine translation systems to improve translation performance. Although early statistical approaches to system combination have been proven effective in analyzing the consensus between hypotheses, they suffer from the error propagation problem due to the use of pipelines. While this problem has been alleviated by end-to-end training of multi-source sequence-to-sequence models recently, these neural models do not explicitly analyze the relations between hypotheses and fail to capture their agreement because the attention to a word in a hypothesis is calculated independently, ignoring the fact that the word might occur in multiple hypotheses. In this work, we propose an approach to modeling voting for system combination in machine translation. The basic idea is to enable words in hypotheses from different systems to vote on words that are representative and should get involved in the generation process. This can be done by quantifying the influence of each voter and its preference for each candidate. Our approach combines the advantages of statistical and neural methods since it can not only analyze the relations between hypotheses but also allow for end-to-end training. Experiments show that our approach is capable of better taking advantage of the consensus between hypotheses and achieves significant improvements over state-of-the-art baselines on Chinese-English and English-German machine translation tasks.


page 1

page 2

page 3

page 4


Agreement-based Joint Training for Bidirectional Attention-based Neural Machine Translation

The attentional mechanism has proven to be effective in improving end-to...

Local System Voting Feature for Machine Translation System Combination

In this paper, we enhance the traditional confusion network system combi...

Syntax-Enhanced Neural Machine Translation with Syntax-Aware Word Representations

Syntax has been demonstrated highly effective in neural machine translat...

LSTM Neural Reordering Feature for Statistical Machine Translation

Artificial neural networks are powerful models, which have been widely a...

The University of Cambridge's Machine Translation Systems for WMT18

The University of Cambridge submission to the WMT18 news translation tas...

Accurate Motion Estimation through Random Sample Aggregated Consensus

We reconsider the classic problem of estimating accurately a 2D transfor...

Distribution Preserving Multiple Hypotheses Prediction for Uncertainty Modeling

Many supervised machine learning tasks, such as future state prediction ...

Please sign up or login with your details

Forgot password? Click here to reset