On Decoding Strategies for Neural Text Generators

Gian Wiher, Clara Meister, Ryan Cotterell


Abstract
When generating text from probabilistic models, the chosen decoding strategy has a profound effect on the resulting text. Yet the properties elicited by various decoding strategies do not always transfer across natural language generation tasks. For example, while mode-seeking methods like beam search perform remarkably well for machine translation, they have been observed to lead to incoherent and repetitive text in story generation. Despite such observations, the effectiveness of decoding strategies is often assessed on only a single task. This work—in contrast—provides a comprehensive analysis of the interaction between language generation tasks and decoding strategies. Specifically, we measure changes in attributes of generated text as a function of both decoding strategy and task using human and automatic evaluation. Our results reveal both previously observed and novel findings. For example, the nature of the diversity–quality trade-off in language generation is very task-specific; the length bias often attributed to beam search is not constant across tasks. https://github.com/gianwiher/decoding-NLG
Anthology ID:
2022.tacl-1.58
Volume:
Transactions of the Association for Computational Linguistics, Volume 10
Month:
Year:
2022
Address:
Cambridge, MA
Editors:
Brian Roark, Ani Nenkova
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
997–1012
Language:
URL:
https://aclanthology.org/2022.tacl-1.58
DOI:
10.1162/tacl_a_00502
Bibkey:
Cite (ACL):
Gian Wiher, Clara Meister, and Ryan Cotterell. 2022. On Decoding Strategies for Neural Text Generators. Transactions of the Association for Computational Linguistics, 10:997–1012.
Cite (Informal):
On Decoding Strategies for Neural Text Generators (Wiher et al., TACL 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-1/2022.tacl-1.58.pdf