TY - GEN
T1 - Text generation with exemplar-based adaptive decoding
AU - Peng, Hao
AU - Parikh, Ankur P.
AU - Faruqui, Manaal
AU - Dhingra, Bhuwan
AU - Das, Dipanjan
N1 - Funding Information:
We thank Antonios Anastasopoulos, Ming-Wei Chang, Michael Collins, Jacob Devlin, Yichen Gong, Luheng He, Kenton Lee, Dianqi Li, Zhouhan Lin, Slav Petrov, Oscar Täckström, Kristina Toutanova, and other members of the Google AI language team for the helpful discussion, and the anonymous reviewers for their valuable feedback.
Publisher Copyright:
© 2019 Association for Computational Linguistics
PY - 2019
Y1 - 2019
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85084055467&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85084055467&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85084055467
T3 - NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference
SP - 2555
EP - 2565
BT - Long and Short Papers
PB - Association for Computational Linguistics (ACL)
T2 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2019
Y2 - 2 June 2019 through 7 June 2019
ER -