paper-with-me

Papers

Beyond Seen Data: Improving KBQA Generalization Through Schema-Guided Logical Form Generation

2025-02-18 · Shengxiang Gao, Jey Han Lau, Jianzhong Qi

Knowledge base question answering (KBQA) aims to answer user questions in natural language using rich human knowledge stored in large KBs. As current KBQA methods struggle with unseen knowledge base elements at test time,we introduce SG-KBQA: a novel model that injects schema contexts into entity retrieval and logical form generation to tackle this issue. It uses the richer semantics and awareness of the knowledge base structure provided by schema contexts to enhance generalizability. We show that SG-KBQA achieves strong generalizability, outperforming state-of-the-art models on two commonly used benchmark datasets across a variety of test settings. Our source code is available at https://github.com/gaosx2000/SG_KBQA.

📄 PDF Abstract BibTeX arXiv:2502.12737

Code (1)

gaosx2000/sg_kbqa 공식 구현 pytorch

Tasks

Entity RetrievalFormKnowledge Base Question AnsweringQuestion AnsweringRetrieval

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases

2020-11-16 · Yu Gu, Sue Kase, Michelle Vanni, Brian Sadler 외

Existing studies on question answering on knowledge bases (KBQA) mainly operate with the standard i.i.d assumption, i.e., training distribution over questions is the same as the test distribution. However, i.i.d may be n…

Knowledge Base Question AnsweringQuestion Answering

Logical Form Generation via Multi-task Learning for Complex Question Answering over Knowledge Bases

2022-10-01 · COLING 2022 10 · Xixin Hu, Xuan Wu, Yiheng Shu, Yuzhong Qu

Question answering over knowledge bases (KBQA) for complex questions is a challenging task in natural language processing. Recently, generation-based methods that translate natural language questions to executable logica…

Entity DisambiguationFormMulti-Task LearningQuestion Answering+2

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

2021-09-17 · ACL 2022 5 · Xi Ye, Semih Yavuz, Kazuma Hashimoto, Yingbo Zhou 외

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 …

Entity LinkingKnowledge Base Question AnsweringQuestion AnsweringZero-shot Generalization

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

2021-11-16 · ACL ARR November 2021 11 · Anonymous

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 …

Entity LinkingKnowledge Base Question AnsweringQuestion AnsweringZero-shot Generalization

FC-KBQA: A Fine-to-Coarse Composition Framework for Knowledge Base Question Answering

2023-06-26 · Lingxi Zhang, Jing Zhang, Yanling Wang, Shulin Cao 외

The generalization problem on KBQA has drawn considerable attention. Existing research suffers from the generalization issue brought by the entanglement in the coarse-grained modeling of the logical expression, or inexec…

Knowledge Base Question AnsweringQuestion Answering