- Conference Paper
We explore the suitability of self-attention models for character-level neural machine translation. We test the standard transformer model, as well as a novel variant in which the encoder block combines information from nearby characters using convolutions. We perform extensive experiments on WMT and UN datasets, testing both bilingual and multilingual translation to English using up to three input languages (French, Spanish, and Chinese). Our transformer variant consistently outperforms the standard transformer at the character-level and converges faster while learning more robust character-level alignments.(1) Show more
Book titleProceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Pages / Article No.
PublisherAssociation for Computational Linguistics
Organisational unit03774 - Hahnloser, Richard H.R. / Hahnloser, Richard H.R.
156976 - Vocal tuning and sequencing in songbirds and in humans (SNF)
NotesDue to the Coronavirus (COVID-19) the conference was conducted virtually.
MoreShow all metadata