CLAug 28, 2018
The University of Cambridge's Machine Translation Systems for WMT18
arXiv:1808.09465v11093 citations
Originality Synthesis-oriented
AI Analysis
This is an incremental improvement for machine translation researchers and practitioners.
The paper tackled machine translation by combining diverse neural models and a phrase-based system, reporting small but consistent gains over strong Transformer ensembles in WMT18 tasks.
The University of Cambridge submission to the WMT18 news translation task focuses on the combination of diverse models of translation. We compare recurrent, convolutional, and self-attention-based neural models on German-English, English-German, and Chinese-English. Our final system combines all neural models together with a phrase-based SMT system in an MBR-based scheme. We report small but consistent gains on top of strong Transformer ensembles.