TempLM: Distilling Language Models into Template-Based Generators

Tianyi Zhang, Mina Lee, Xiang Lisa Li, Ende Shen, Tatsunori Hashimoto


Abstract
While pretrained language models (PLMs) have greatly improved text generation, they have also been known to produce unfaithful or inappropriate content. In contrast, classic template-based systems provide strong guarantees of faithfulness at the cost of fluency. We propose TempLM, which achieves the best of both worlds by distilling a PLM into a template-based generator. On the E2E and SynthBio data-to-text datasets, we show that TempLM is more faithful than the original PLM and is more fluent than prior template systems. Notably, on an out-of-domain evaluation, TempLM reduces a finetuned BART model’s unfaithfulness rate from 83% to 0%. In a human study, we find that TempLM’s templates substantially improve upon human-written ones in BERTScore.
Anthology ID:
2023.findings-acl.124
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1970–1994
Language:
URL:
https://aclanthology.org/2023.findings-acl.124
DOI:
Bibkey:
Cite (ACL):
Tianyi Zhang, Mina Lee, Xiang Lisa Li, Ende Shen, and Tatsunori Hashimoto. 2023. TempLM: Distilling Language Models into Template-Based Generators. In Findings of the Association for Computational Linguistics: ACL 2023, pages 1970–1994, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
TempLM: Distilling Language Models into Template-Based Generators (Zhang et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nodalida-main-page/2023.findings-acl.124.pdf