Non-Monotonic Sequential Text Generation

Sean Welleck, Kianté Brantley, Hal Daumé Iii, Kyunghyun Cho
Proceedings of the 36th International Conference on Machine Learning, PMLR 97:6716-6726, 2019.

Abstract

Standard sequential generation methods assume a pre-specified generation order, such as text generation methods which generate words from left to right. In this work, we propose a framework for training models of text generation that operate in non-monotonic orders; the model directly learns good orders, without any additional annotation. Our framework operates by generating a word at an arbitrary position, and then recursively generating words to its left and then words to its right, yielding a binary tree. Learning is framed as imitation learning, including a coaching method which moves from imitating an oracle to reinforcing the policy’s own preferences. Experimental results demonstrate that using the proposed method, it is possible to learn policies which generate text without pre-specifying a generation order, while achieving competitive performance with conventional left-to-right generation.

Cite this Paper

BibTeX
@InProceedings{pmlr-v97-welleck19a, title = {Non-Monotonic Sequential Text Generation}, author = {Welleck, Sean and Brantley, Kiant{\'e} and Iii, Hal Daum{\'e} and Cho, Kyunghyun}, booktitle = {Proceedings of the 36th International Conference on Machine Learning}, pages = {6716--6726}, year = {2019}, editor = {Chaudhuri, Kamalika and Salakhutdinov, Ruslan}, volume = {97}, series = {Proceedings of Machine Learning Research}, month = {09--15 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v97/welleck19a/welleck19a.pdf}, url = {https://proceedings.mlr.press/v97/welleck19a.html}, abstract = {Standard sequential generation methods assume a pre-specified generation order, such as text generation methods which generate words from left to right. In this work, we propose a framework for training models of text generation that operate in non-monotonic orders; the model directly learns good orders, without any additional annotation. Our framework operates by generating a word at an arbitrary position, and then recursively generating words to its left and then words to its right, yielding a binary tree. Learning is framed as imitation learning, including a coaching method which moves from imitating an oracle to reinforcing the policy’s own preferences. Experimental results demonstrate that using the proposed method, it is possible to learn policies which generate text without pre-specifying a generation order, while achieving competitive performance with conventional left-to-right generation.} }
Endnote
%0 Conference Paper %T Non-Monotonic Sequential Text Generation %A Sean Welleck %A Kianté Brantley %A Hal Daumé Iii %A Kyunghyun Cho %B Proceedings of the 36th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Ruslan Salakhutdinov %F pmlr-v97-welleck19a %I PMLR %P 6716--6726 %U https://proceedings.mlr.press/v97/welleck19a.html %V 97 %X Standard sequential generation methods assume a pre-specified generation order, such as text generation methods which generate words from left to right. In this work, we propose a framework for training models of text generation that operate in non-monotonic orders; the model directly learns good orders, without any additional annotation. Our framework operates by generating a word at an arbitrary position, and then recursively generating words to its left and then words to its right, yielding a binary tree. Learning is framed as imitation learning, including a coaching method which moves from imitating an oracle to reinforcing the policy’s own preferences. Experimental results demonstrate that using the proposed method, it is possible to learn policies which generate text without pre-specifying a generation order, while achieving competitive performance with conventional left-to-right generation.
APA
Welleck, S., Brantley, K., Iii, H.D. & Cho, K.. (2019). Non-Monotonic Sequential Text Generation. Proceedings of the 36th International Conference on Machine Learning, in Proceedings of Machine Learning Research 97:6716-6726 Available from https://proceedings.mlr.press/v97/welleck19a.html.

Related Material