ReasoningLM: Enabling Structural Subgraph Reasoning in Pre-trained Language Models for Question Answering over Knowledge Graph

Jinhao Jiang, Kun Zhou, Xin Zhao, Yaliang Li, Ji-Rong Wen


Abstract
Question Answering over Knowledge Graph (KGQA) aims to seek answer entities for the natural language question from a large-scale Knowledge Graph (KG). To better perform reasoning on KG, recent work typically adopts a pre-trained language model (PLM) to model the question, and a graph neural network (GNN) based module to perform multi-hop reasoning on the KG. Despite the effectiveness, due to the divergence in model architecture, the PLM and GNN are not closely integrated, limiting the knowledge sharing and fine-grained feature interactions. To solve it, we aim to simplify the above two-module approach, and develop a more capable PLM that can directly support subgraph reasoning for KGQA, namely ReasoningLM. In our approach, we propose a subgraph-aware self-attention mechanism to imitate the GNN for performing structured reasoning, and also adopt an adaptation tuning strategy to adapt the model parameters with 20,000 subgraphs with synthesized questions. After adaptation, the PLM can be parameter-efficient fine-tuned on downstream tasks. Experiments show that ReasoningLM surpasses state-of-the-art models by a large margin, even with fewer updated parameters and less training data. Our codes and data are publicly available at https://github.com/RUCAIBox/ReasoningLM.
Anthology ID:
2023.emnlp-main.228
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3721–3735
Language:
URL:
https://aclanthology.org/2023.emnlp-main.228
DOI:
10.18653/v1/2023.emnlp-main.228
Bibkey:
Cite (ACL):
Jinhao Jiang, Kun Zhou, Xin Zhao, Yaliang Li, and Ji-Rong Wen. 2023. ReasoningLM: Enabling Structural Subgraph Reasoning in Pre-trained Language Models for Question Answering over Knowledge Graph. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 3721–3735, Singapore. Association for Computational Linguistics.
Cite (Informal):
ReasoningLM: Enabling Structural Subgraph Reasoning in Pre-trained Language Models for Question Answering over Knowledge Graph (Jiang et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.228.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.228.mp4