Text Generation with Exemplar-based Adaptive Decoding

Hao Peng, Ankur Parikh, Manaal Faruqui, Bhuwan Dhingra, Dipanjan Das


Abstract
We propose a novel conditioned text generation model. It draws inspiration from traditional template-based text generation techniques, where the source provides the content (i.e., what to say), and the template influences how to say it. Building on the successful encoder-decoder paradigm, it first encodes the content representation from the given input text; to produce the output, it retrieves exemplar text from the training data as “soft templates,” which are then used to construct an exemplar-specific decoder. We evaluate the proposed model on abstractive text summarization and data-to-text generation. Empirical results show that this model achieves strong performance and outperforms comparable baselines.
Anthology ID:
N19-1263
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Jill Burstein, Christy Doran, Thamar Solorio
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2555–2565
Language:
URL:
https://aclanthology.org/N19-1263
DOI:
10.18653/v1/N19-1263
Bibkey:
Cite (ACL):
Hao Peng, Ankur Parikh, Manaal Faruqui, Bhuwan Dhingra, and Dipanjan Das. 2019. Text Generation with Exemplar-based Adaptive Decoding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 2555–2565, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Text Generation with Exemplar-based Adaptive Decoding (Peng et al., NAACL 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/N19-1263.pdf
Supplementary:
 N19-1263.Supplementary.pdf
Data
New York Times Annotated CorpusWikiBio