Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals

By Gaole He, Yunshi Lan, Jing Jiang, Wayne Xin Zhao, Ji-rong Wen. Web Search and Data Mining, 2021

295 citations recorded by the source corpus.

Multi-hop Knowledge Base Question Answering (KBQA) aims to find the answer entities that are multiple hops away in the Knowl- edge Base (KB) from the entities in the question. A major challenge is the lack of supervision signals at intermediate steps. Therefore, multi-hop KBQA algorithms can only receive the feedback from the final answer, which makes the learning unstable or ineffective. To address this challenge, we propose a novel teacher-student approach for the multi-hop KBQA task. In our approach, the stu- dent network aims to find the correct answer to the query, while the teacher network tries to learn intermediate supervision signals for improving the reasoning capacity of the student network. The major novelty lies in the design of the teacher network, where we utilize both forward and backward reasoning to enhance the learning of intermediate entity distributions. By considering bidi- rectional reasoning, the teacher network can produce more reliable intermediate supervision signals, which can alleviate the issue of spurious reasoning. Extensive experiments on three benchmark datasets have demonstrated the effectiveness of our approach on the KBQA task.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/34ba905d57042bafc761e18284cfa29b6aaaa6e6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning (2023, methodology): “(Miller et al., 2016; He et al., 2021; Yasunaga et al., 2021).”
Graph Retrieval-Augmented Generation: A Survey (2024, unknown): “[102],[142],[181],[168],[42],[155],[58],[60],[101],[152],[3],[136],[90],[108],[139],[179],[23],[35],[100],[4],[133],[46],[61],[17],[140],[62] Accuracy,Hits@1,EM, Recall,F1, BERTScore, GPT-4AverageRanking WebQ[5] [159],[142],[52],[168],[107],[62] CWQ[144]…”
Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph (2023, unknown): “Do different KGs affect ToG’s performance?”
StructGPT: A General Framework for Large Language Model to Reason over Structured Data (2023, methodology): “Following existing work (Sun et al., 2018; He et al., 2021), we denote the mentioned entities in the given question q as the topic entity eT , and assume it has been linked to some specific entity on the KG.”