Building the Directed Semantic Graph for Coherent Long Text Generation

Ziao Wang, Xiaofeng Zhang, Hongwei Du


Abstract
Generating long text conditionally depending on the short input text has recently attracted more and more research efforts. Most existing approaches focus more on introducing extra knowledge to supplement the short input text, but ignore the coherence issue of the generated texts. To address aforementioned research issue, this paper proposes a novel two-stage approach to generate coherent long text. Particularly, we first build a document-level path for each output text with each sentence embedding as its node, and a revised self-organising map (SOM) is proposed to cluster similar nodes of a family of document-level paths to construct the directed semantic graph. Then, three subgraph alignment methods are proposed to extract the maximum matching paths or subgraphs. These directed subgraphs are considered to well preserve extra but relevant content to the short input text, and then they are decoded by the employed pre-trained model to generate coherent long text. Extensive experiments have been performed on three real-world datasets, and the promising results demonstrate that the proposed approach is superior to the state-of-the-art approaches w.r.t. a number of evaluation criteria.
Anthology ID:
2021.emnlp-main.200
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2563–2572
Language:
URL:
https://aclanthology.org/2021.emnlp-main.200
DOI:
10.18653/v1/2021.emnlp-main.200
Bibkey:
Cite (ACL):
Ziao Wang, Xiaofeng Zhang, and Hongwei Du. 2021. Building the Directed Semantic Graph for Coherent Long Text Generation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2563–2572, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Building the Directed Semantic Graph for Coherent Long Text Generation (Wang et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.200.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.200.mp4