Poster
Sequence Modeling with Unconstrained Generation Order
Dmitrii Emelianenko · Elena Voita · Pavel Serdyukov

Wed Dec 11th 10:45 AM -- 12:45 PM @ East Exhibition Hall B + C #121

The dominant approach to sequence generation is to produce a sequence in some predefined order, e.g. left to right. In contrast, we propose a more general model that can generate the output sequence by inserting tokens in any arbitrary order. Our model learns decoding order as a result of its training procedure. Our experiments show that this model is superior to fixed order models on a number of sequence generation tasks, such as Machine Translation, Image-to-LaTeX and Image Captioning.

Author Information

Dmitrii Emelianenko (Yandex; National Research University Higher School of Economics)
Lena Voita (Yandex; University of Amsterdam)
Pavel Serdyukov (Yandex)

More from the Same Authors