Controlling Politeness in Neural Machine Translation via Side Constraints

@inproceedings{Sennrich2016ControllingPI,
  title={Controlling Politeness in Neural Machine Translation via Side Constraints},
  author={Rico Sennrich and B. Haddow and Alexandra Birch},
  booktitle={HLT-NAACL},
  year={2016}
}
Many languages use honorifics to express politeness, social distance, or the relative social status between the speaker and their addressee(s. [...] Key Method We show that by marking up the (English) source side of the training data with a feature that encodes the use of honorifics on the (German) target side, we can control the honorifics produced at test time. Experiments show that the choice of honorifics has a big impact on translation quality as measured by BLEU, and oracle experiments show that…Expand
Controlling Japanese Honorifics in English-to-Japanese Neural Machine Translation
Lost in Back-Translation: Emotion Preservation in Neural Machine Translation
Polite Dialogue Generation Without Parallel Data
  • Tong Niu, Mohit Bansal
  • Computer Science
  • Transactions of the Association for Computational Linguistics
  • 2018
Neural MultiVoice Models for Expressing Novel Personalities in Dialog
Integrating and Evaluating Extra-linguistic Context in Neural Machine Translation First
  • 2019
Getting Gender Right in Neural Machine Translation
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 23 REFERENCES
Neural Machine Translation of Rare Words with Subword Units
Montreal Neural Machine Translation Systems for WMT'15
Neural Machine Translation by Jointly Learning to Align and Translate
Machine Translation for Subtitling: A Large-Scale Evaluation
On Using Very Large Target Vocabulary for Neural Machine Translation
Larger-Context Language Modelling
Annotating Honorifics Denoting Social Ranking of Referents
...
1
2
3
...