GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text Generation

Anthony Colas, Mehrdad Alvandipour, Daisy Zhe Wang


Abstract
Recent improvements in KG-to-text generation are due to additional auxiliary pre-training tasks designed to give the fine-tune task a boost in performance. These tasks require extensive computational resources while only suggesting marginal improvements. Here, we demonstrate that by fusing graph-aware elements into existing pre-trained language models, we are able to outperform state-of-the-art models and close the gap imposed by additional pre-training tasks. We do so by proposing a mask structure to capture neighborhood information and a novel type encoder that adds a bias to the graph-attention weights depending on the connection type. Experiments on two KG-to-text benchmark datasets show our models are competitive while involving fewer parameters and no additional pre-training tasks. By formulating the problem as a framework, we can interchange the various proposed components and begin interpreting KG-to-text generative models based on the topological and type information found in a graph.
Anthology ID:
2022.coling-1.506
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
5755–5769
Language:
URL:
https://aclanthology.org/2022.coling-1.506
DOI:
Bibkey:
Cite (ACL):
Anthony Colas, Mehrdad Alvandipour, and Daisy Zhe Wang. 2022. GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text Generation. In Proceedings of the 29th International Conference on Computational Linguistics, pages 5755–5769, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text Generation (Colas et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.506.pdf