Bridging the Structural Gap Between Encoding and Decoding for Data-To-Text Generation

Chao Zhao, Marilyn Walker, Snigdha Chaturvedi


Abstract
Generating sequential natural language descriptions from graph-structured data (e.g., knowledge graph) is challenging, partly because of the structural differences between the input graph and the output text. Hence, popular sequence-to-sequence models, which require serialized input, are not a natural fit for this task. Graph neural networks, on the other hand, can better encode the input graph but broaden the structural gap between the encoder and decoder, making faithful generation difficult. To narrow this gap, we propose DualEnc, a dual encoding model that can not only incorporate the graph structure, but can also cater to the linear structure of the output text. Empirical comparisons with strong single-encoder baselines demonstrate that dual encoding can significantly improve the quality of the generated text.
Anthology ID:
2020.acl-main.224
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2481–2491
Language:
URL:
https://aclanthology.org/2020.acl-main.224
DOI:
10.18653/v1/2020.acl-main.224
Bibkey:
Cite (ACL):
Chao Zhao, Marilyn Walker, and Snigdha Chaturvedi. 2020. Bridging the Structural Gap Between Encoding and Decoding for Data-To-Text Generation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 2481–2491, Online. Association for Computational Linguistics.
Cite (Informal):
Bridging the Structural Gap Between Encoding and Decoding for Data-To-Text Generation (Zhao et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.224.pdf
Video:
 http://slideslive.com/38929169