NeurIPS 2019poster25 citations
Sequence Modeling with Unconstrained Generation Order
Dmitrii Emelianenko, Elena Voita, Pavel Serdyukov
Abstract
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.
BibTeX
@inproceedings{NEURIPS2019_1558417b,
author = {Emelianenko, Dmitrii and Voita, Elena and Serdyukov, Pavel},
booktitle = {Advances in Neural Information Processing Systems},
editor = {H. Wallach and H. Larochelle and A. Beygelzimer and F. d\textquotesingle Alch\'{e}-Buc and E. Fox and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {Sequence Modeling with Unconstrained Generation Order},
url = {https://proceedings.neurips.cc/paper_files/paper/2019/file/1558417b096b5d8e7cbe0183ea9cbf26-Paper.pdf},
volume = {32},
year = {2019}
}