Mutual Information and Diverse Decoding Improve Neural Machine Translation

Explore this paper's citation graph

Summary

This work introduces an alternative objective function for neural MT that maximizes the mutual information between the source and target sentences, modeling the bi-directional dependency of sources and targets.

Type
preprint
Published
2016-01-04
Cited by
129
References
39
Access
Open access

Keywords

Decoding methods, Machine translation, Computer science, Translation (biology), Neural decoding

References

Cited by

Related papers