mlsanityData to 7 Oct 2026

Two is Better Than One: Answering Complex Questions by Multiple Knowledge Sources with Generalized Links

arXiv 2309.05201 ↗First posted 11 Sep 2023cs.CLcited by 2

Not on the map. Why?

Abstract (arXiv)

Incorporating multiple knowledge sources is proven to be beneficial for answering complex factoid questions. To utilize multiple knowledge bases (KB), previous works merge all KBs into a single graph via entity alignment and reduce the problem to question-answering (QA) over the fused KB. In reality, various link relations between KBs might be adopted in QA over multi-KBs. In addition to the identity between the alignable entities (i.e. full link), unalignable entities expressing the different aspects or types of an abstract concept may also be treated identical in a question (i.e. partial link). Hence, the KB fusion in prior works fails to represent all types of links, restricting their ability to comprehend multi-KBs for QA. In this work, we formulate the novel Multi-KB-QA task that leverages the full and partial links among multiple KBs to derive correct answers, a benchmark with diversified link and query types is also constructed to efficiently evaluate Multi-KB-QA performance. Finally, we propose a method for Multi-KB-QA that encodes all link relations in the KB embedding to score and rank candidate answers. Experiments show that our method markedly surpasses conventional KB-QA systems in Multi-KB-QA, justifying the necessity of devising this task.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 17 of its 41 references that are in the map. First posted on arXiv 11 Sep 2023.

Builds on

17 of 41 references.

References · 17

  1. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  2. 2016Complex Embeddings for Simple Link Predictioncited by 897
  3. 2019TuckER: Tensor Factorization for Knowledge Graph Completioncited by 290
  4. 2019PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Textcited by 182
  5. 2020Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddingscited by 169
  6. 2020Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Basescited by 169
  7. 2015Large-scale Simple Question Answering with Memory Networkscited by 127
  8. 2019Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answeringcited by 68
  9. 2020UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answeringcited by 61
  10. 2019KnowIT VQA: Answering Knowledge-Based Questions about Videoscited by 53
  11. 2016Question Answering on Freebase via Relation Extraction and Textual Evidencecited by 39
  12. 2018SimpleQuestions Nearly Solved: A New Upperbound and Baseline Approachcited by 18
5 more
  1. 2021Outlining and Filling: Hierarchical Query Graph Generation for Answering Complex Questions over Knowledge Graphscited by 16
  2. 2020Improving Commonsense Question Answering by Graph-based Iterative Retrieval over Multiple Knowledge Sourcescited by 14
  3. 2018LinkNBed: Multi-Graph Representation Learning with Entity Linkagecited by 10
  4. 2022Crake: Causal-Enhanced Table-Filler for Question Answering over Large Scale Knowledge Basecited by 8
  5. 2022μKG: A Library for Multi-source Knowledge Graph Embeddings and Applicationscited by 4

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025DBRouting: Routing End User Queries to Databases for Answerabilitycited by 1
  2. 2025SEAL: Self-Evolving Agentic Learning for Conversational Question Answering over Knowledge Graphscited by 1