Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

First the worst: Finding better gender translations during beam search



Danielle Saunders , Rosie Sallis , Bill Byrne


   Access Paper or Ask Questions

Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey



Danielle Saunders

* 39 pages + references 

   Access Paper or Ask Questions

Inference-only sub-character decomposition improves translation of unseen logographic characters



Danielle Saunders , Weston Feely , Bill Byrne

* Workshop on Asian Translation (WAT) 2020 

   Access Paper or Ask Questions

Addressing Exposure Bias With Document Minimum Risk Training: Cambridge at the WMT20 Biomedical Translation Task



Danielle Saunders , Bill Byrne

* WMT20 biomedical task 

   Access Paper or Ask Questions

Neural Machine Translation Doesn't Translate Gender Coreference Right Unless You Make It



Danielle Saunders , Rosie Sallis , Bill Byrne

* Workshop on Gender Bias in NLP, 2020 

   Access Paper or Ask Questions

Using Context in Neural Machine Translation Training Objectives



Danielle Saunders , Felix Stahlberg , Bill Byrne

* ACL 2020 

   Access Paper or Ask Questions

Reducing Gender Bias in Neural Machine Translation as a Domain Adaptation Problem



Danielle Saunders , Bill Byrne

* ACL 2020 

   Access Paper or Ask Questions

UCAM Biomedical translation at WMT19: Transfer learning multi-domain ensembles



Danielle Saunders , Felix Stahlberg , Bill Byrne

* To appear at WMT19 

   Access Paper or Ask Questions

[email protected]:ewc&lms



Felix Stahlberg , Danielle Saunders , Adria de Gispert , Bill Byrne

* WMT2019 system description (University of Cambridge) 

   Access Paper or Ask Questions

1
2
>>