arXiv Open Access 2018

The University of Cambridge's Machine Translation Systems for WMT18

Felix Stahlberg Adria de Gispert Bill Byrne

Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

cs.CL

Penulis (3)

Felix Stahlberg

Adria de Gispert

Bill Byrne

Format Sitasi

APA MLA BibTeX

Stahlberg, F., Gispert, A.d., Byrne, B. (2018). The University of Cambridge's Machine Translation Systems for WMT18. https://arxiv.org/abs/1808.09465

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2018
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓