Controlling Politeness in Neural Machine Translation via Side Constraints

By Rico Sennrich, Barry Haddow, Alexandra Birch. 2016

340 citations recorded by the source corpus.

Many languages use honorifics to express politeness, social distance, or the relative social status between the speaker and their ad-dressee(s). In machine translation from a language without honorifics such as English, it is difficult to predict the appropriate honorific, but users may want to control the level of politeness in the output. In this paper, we perform a pilot study to control honorifics in neural machine translation (NMT) via side constraints , focusing on English → German. We show that by marking up the (English) source side of the training data with a feature that en-codes 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 B LEU , and oracle experiments show that substantial im-provements are possible by constraining the translation to the desired level of politeness.

Subfields: Artificial Intelligence, Machine Translation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Graham Neubig
  2. Yonatan Belinkov
  3. Mohit Bansal
  4. Luke S. Zettlemoyer
  5. Percy Liang
  6. Yoav Goldberg
  7. Jianfeng Gao
  8. Noah A. Smith

In Machine Translation

  1. Yonatan Belinkov
  2. Nadir Durrani
  3. Hassan Sajjad
  4. Philipp Koehn
  5. Fahim Dalvi
  6. Sudha Rao
  7. Markus Freitag
  8. Matteo Negri

Citations in the corpus