Improving Chinese Story Generation via Awareness of Syntactic Dependencies and Semantics

Henglin Huang, Chen Tang, Tyler Loakman, Frank Guerin, Chenghua Lin


Abstract
Story generation aims to generate a long narrative conditioned on a given input. In spite of the success of prior works with the application of pre-trained models, current neural models for Chinese stories still struggle to generate high-quality long text narratives. We hypothesise that this stems from ambiguity in syntactically parsing the Chinese language, which does not have explicit delimiters for word segmentation. Consequently, neural models suffer from the inefficient capturing of features in Chinese narratives. In this paper, we present a new generation framework that enhances the feature capturing mechanism by informing the generation model of dependencies between words and additionally augmenting the semantic representation learning through synonym denoising training. We conduct a range of experiments, and the results demonstrate that our framework outperforms the state-of-the-art Chinese generation models on all evaluation metrics, demonstrating the benefits of enhanced dependency and semantic representation learning.
Anthology ID:
2022.aacl-short.23
Volume:
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Month:
November
Year:
2022
Address:
Online only
Editors:
Yulan He, Heng Ji, Sujian Li, Yang Liu, Chua-Hui Chang
Venues:
AACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
178–185
Language:
URL:
https://aclanthology.org/2022.aacl-short.23
DOI:
Bibkey:
Cite (ACL):
Henglin Huang, Chen Tang, Tyler Loakman, Frank Guerin, and Chenghua Lin. 2022. Improving Chinese Story Generation via Awareness of Syntactic Dependencies and Semantics. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 178–185, Online only. Association for Computational Linguistics.
Cite (Informal):
Improving Chinese Story Generation via Awareness of Syntactic Dependencies and Semantics (Huang et al., AACL-IJCNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.aacl-short.23.pdf