Exploring the Synergy of Dual-path Encoder and Alignment Module for Better Graph-to-Text Generation
Tianxin Zhao, Yingxin Liu, Xiangdong Su, Jiang Li, Guanglai Gao
Abstract
The mainstream approaches view the knowledge graph-to-text (KG-to-text) generation as a sequence-to-sequence task and fine-tune the pre-trained model (PLM) to generate the target text from the linearized knowledge graph. However, the linearization of knowledge graphs and the structure of PLMs lead to the loss of a large amount of graph structure information. Moreover, PLMs lack an explicit graph-text alignment strategy because of the discrepancy between structural and textual information. To solve these two problems, we propose a synergetic KG-to-text model with a dual-path encoder, an alignment module, and a guidance module. The dual-path encoder consists of a graph structure encoder and a text encoder, which can better encode the structure and text information of the knowledge graph. The alignment module contains a two-layer Transformer block and an MLP block, which aligns and integrates the information from the dual encoder. The guidance module combines an improved pointer network and an MLP block to avoid error-generated entities and ensures the fluency and accuracy of the generated text. Our approach obtains very competitive performance on three benchmark datasets. Our code is available from https://github.com/IMu-MachineLearningsxD/G2T.- Anthology ID:
- 2024.lrec-main.612
- Volume:
- Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
- Month:
- May
- Year:
- 2024
- Address:
- Torino, Italia
- Editors:
- Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
- Venues:
- LREC | COLING
- SIG:
- Publisher:
- ELRA and ICCL
- Note:
- Pages:
- 6980–6991
- Language:
- URL:
- https://aclanthology.org/2024.lrec-main.612
- DOI:
- Cite (ACL):
- Tianxin Zhao, Yingxin Liu, Xiangdong Su, Jiang Li, and Guanglai Gao. 2024. Exploring the Synergy of Dual-path Encoder and Alignment Module for Better Graph-to-Text Generation. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 6980–6991, Torino, Italia. ELRA and ICCL.
- Cite (Informal):
- Exploring the Synergy of Dual-path Encoder and Alignment Module for Better Graph-to-Text Generation (Zhao et al., LREC-COLING 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.lrec-main.612.pdf