Conditional Poisson Stochastic Beams

Clara Meister, Afra Amini, Tim Vieira, Ryan Cotterell


Abstract
Beam search is the default decoding strategy for many sequence generation tasks in NLP. The set of approximate K-best items returned by the algorithm is a useful summary of the distribution for many applications; however, the candidates typically exhibit high overlap and may give a highly biased estimate for expectations under our model. These problems can be addressed by instead using stochastic decoding strategies. In this work, we propose a new method for turning beam search into a stochastic process: Conditional Poisson stochastic beam search. Rather than taking the maximizing set at each iteration, we sample K candidates without replacement according to the conditional Poisson sampling design. We view this as a more natural alternative to Kool et al. (2019)’s stochastic beam search (SBS). Furthermore, we show how samples generated under the CPSBS design can be used to build consistent estimators and sample diverse sets from sequence models. In our experiments, we observe CPSBS produces lower variance and more efficient estimators than SBS, even showing improvements in high entropy settings.
Anthology ID:
2021.emnlp-main.52
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
664–681
Language:
URL:
https://aclanthology.org/2021.emnlp-main.52
DOI:
10.18653/v1/2021.emnlp-main.52
Bibkey:
Cite (ACL):
Clara Meister, Afra Amini, Tim Vieira, and Ryan Cotterell. 2021. Conditional Poisson Stochastic Beams. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 664–681, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Conditional Poisson Stochastic Beams (Meister et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.52.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.52.mp4