CLJun 13, 2023

Question Decomposition Tree for Answering Complex Questions over Knowledge Bases

arXiv:2306.07597v133 citationsh-index: 32
Originality Incremental advance
AI Analysis

This work addresses the challenge of handling multiple compositionality types in complex questions for knowledge base question answering, representing an incremental improvement over existing decomposition methods.

The paper tackles the problem of answering complex questions over knowledge bases by proposing a Question Decomposition Tree (QDT) to represent question structure, and shows that their QDTQA system outperforms previous state-of-the-art methods on the ComplexWebQuestions dataset and improves an existing system by 12% on LC-QuAD 1.0.

Knowledge base question answering (KBQA) has attracted a lot of interest in recent years, especially for complex questions which require multiple facts to answer. Question decomposition is a promising way to answer complex questions. Existing decomposition methods split the question into sub-questions according to a single compositionality type, which is not sufficient for questions involving multiple compositionality types. In this paper, we propose Question Decomposition Tree (QDT) to represent the structure of complex questions. Inspired by recent advances in natural language generation (NLG), we present a two-staged method called Clue-Decipher to generate QDT. It can leverage the strong ability of NLG model and simultaneously preserve the original questions. To verify that QDT can enhance KBQA task, we design a decomposition-based KBQA system called QDTQA. Extensive experiments show that QDTQA outperforms previous state-of-the-art methods on ComplexWebQuestions dataset. Besides, our decomposition method improves an existing KBQA system by 12% and sets a new state-of-the-art on LC-QuAD 1.0.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes