PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models

Torsten Scholak, Nathan Schucher, Dzmitry Bahdanau


Abstract
Large pre-trained language models for textual data have an unconstrained output space; at each decoding step, they can produce any of 10,000s of sub-word tokens. When fine-tuned to target constrained formal languages like SQL, these models often generate invalid code, rendering it unusable. We propose PICARD (code available at https://github.com/ElementAI/picard), a method for constraining auto-regressive decoders of language models through incremental parsing. PICARD helps to find valid output sequences by rejecting inadmissible tokens at each decoding step. On the challenging Spider and CoSQL text-to-SQL translation tasks, we show that PICARD transforms fine-tuned T5 models with passable performance into state-of-the-art solutions.
Anthology ID:
2021.emnlp-main.779
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:
9895–9901
Language:
URL:
https://aclanthology.org/2021.emnlp-main.779
DOI:
10.18653/v1/2021.emnlp-main.779
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.779.pdf
Code
 ElementAI/picard
Data
CoSQLSPIDER