RNG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering

By Xi Ye, Semih Yavuz, Kazuma Hashimoto, Yingbo Zhou, Caiming Xiong. 2021

212 citations recorded by the source corpus.

Existing KBQA approaches, despite achieving strong performance on i.i.d. test data, often struggle in generalizing to questions involving unseen KB schema items. Prior ranking-based approaches have shown some success in generalization, but suffer from the coverage issue. We present RnG-KBQA, a Rank-and-Generate approach for KBQA, which remedies the coverage issue with a generation model while preserving a strong generalization capability. Our approach first uses a contrastive ranker to rank a set of candidate logical forms obtained by searching over the knowledge graph. It then introduces a tailored generation model conditioned on the question and the top-ranked candidates to compose the final logical form. We achieve new state-of-the-art results on GrailQA and WebQSP datasets. In particular, our method surpasses the prior state-of-the-art by a large margin on the GrailQA leaderboard. In addition, RnG-KBQA outperforms all prior approaches on the popular WebQSP benchmark, even including the ones that use the oracle entity linking. The experimental results demonstrate the effectiveness of the interplay between ranking and generation, which leads to the superior performance of our proposed approach across all settings with especially strong improvements in zero-shot generalization.

Subfields: Artificial Intelligence, Question Answering & Reading Comprehension, Knowledge Graphs & Representation

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 Question Answering & Reading Comprehension

In Knowledge Graphs & Representation

Citations in the corpus

UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models (2022, methodology): “U NIFIED SKG is a challenging testbed for few-shot (Brown et al., 2020; Ye et al., 2021a) and zero-shot learning (Zhong et al., 2021; Wei et al., 2021; Sanh et al., 2021) with PLMs.”
Retrieval-Augmented Generation for AI-Generated Content: A Survey (2024, unknown): “Therefore, RAG methods which involve knowledge graph can use k -hop neighbor search as retrieval process [123], [124].”
Graph Retrieval-Augmented Generation: A Survey (2024, unknown): “While, GraphRAG methods leverage explicit entity and relationship representations in graph data, enabling precise answers by retrieving relevant structured information.”
Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning (2023, methodology): “• RnG-KBQA (Ye et al., 2022) first enumerates all possible queries and then ranks them to get the final output.”