2 papers
cs.CL2022
The University of Edinburgh's Submission to the WMT22 Code-Mixing Shared Task (MixMT)
Faheem Kirefu, Vivek Iyer, Pinzhen Chen +1
The University of Edinburgh participated in the WMT22 shared task on code-mixed translation. This consists of two subtasks: i) generating code-mixed Hindi/English (Hinglish) text g…
cs.CL2021
The Highs and Lows of Simple Lexical Domain Adaptation Approaches for Neural Machine Translation
Nikolay Bogoychev, Pinzhen Chen
Machine translation systems are vulnerable to domain mismatch, especially in a low-resource scenario. Out-of-domain translations are often of poor quality and prone to hallucinatio…