mlsanityData to 7 Oct 2026

Question Decomposition Tree for Answering Complex Questions over Knowledge Bases

arXiv 2306.07597 ↗First posted 13 Jun 2023cs.CLcited by 15

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 14 of its 28 references that are in the map. First posted on arXiv 13 Jun 2023.

Builds on

14 of 28 references.

References · 14

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2018The Web as a Knowledge-base for Answering Complex Questionscited by 409
  4. 2019PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Textcited by 182
  5. 2020Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Basescited by 169
  6. 2020Break It Down: A Question Understanding Benchmarkcited by 131
  7. 2019Multi-hop Reading Comprehension through Question Decomposition and Rescoringcited by 119
  8. 2021Case-based Reasoning for Natural Language Queries over Knowledge Basescited by 107
  9. 2021RnG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answeringcited by 86
  10. 2021A Survey on Complex Knowledge Base Question Answering: Methods, Challenges and Solutionscited by 77
  11. 2020Efficient One-Pass End-to-End Entity Linking for Questionscited by 76
  12. 2020Leveraging Abstract Meaning Representation for Knowledge Base Question Answeringcited by 53
2 more
  1. 2021Formal Query Building with Query Structure Prediction for Complex Question Answering over Knowledge Basecited by 16
  2. 2021A Two-Stage Approach towards Generalization in Knowledge Base Question Answeringcited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 5; 2025: 5; 2026: 2.

15 papers.

Sort:

By area:

  1. 2023Semantic Decomposition of Question and SQL for Text-to-SQL Parsingcited by 13
  2. 2025iQUEST: An Iterative Question-Guided Framework for Knowledge Base Question Answeringcited by 8
  3. 2025Atomic Skills are the Prerequisite: When Reinforcement Learning Synthesizes Compositional Reasoning, and When It Only Amplifiescited by 8
  4. 2023MarkQA: A large scale KBQA dataset with numerical reasoningcited by 6
  5. 2024SPARKLE: Enhancing SPARQL Generation with Direct KG Integration in Decodingcited by 5
  6. 2024UniHGKR: Unified Instruction-aware Heterogeneous Knowledge Retrieverscited by 5
  7. 2024TARGA: Targeted Synthetic Data Generation for Practical Reasoning over Structured Datacited by 5
  8. 2023Data Distribution Bottlenecks in Grounding Language Models to Knowledge Basescited by 3
  9. 2024Timeline-based Sentence Decomposition with In-Context Learning for Temporal Fact Extractioncited by 3
  10. 2025HyFedRAG: A Federated Retrieval-Augmented Generation Framework for Heterogeneous and Privacy-Sensitive Datacited by 3
  11. 2025Diverse In-Context Example Selection After Decomposing Programs and Aligned Utterances Improves Semantic Parsingcited by 1
  12. 2024Question Answering Over Spatio-Temporal Knowledge Graphcited by 0
3 more
  1. 2025Neurosymbolic Feature Extraction for Identifying Forced Labor in Supply Chainscited by 0
  2. 2026CMT-RAG: Complementary Memory Traces for Multi-turn Multi-hop RAGcited by 0
  3. 2026X-Tree: Tokenizing Reusable Experience for Efficient Agent Generalizationcited by 0