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

arXiv: https://arxiv.org/abs/2309.05201 · HTML: https://mlsanity.com/paper/2309.05201/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 41 references that are in the map.
- First posted on arXiv 11 Sep 2023.

## Builds on (most cited first, 17 of 17)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [TuckER: Tensor Factorization for Knowledge Graph Completion](https://mlsanity.com/paper/1901.09590/) (2019)
- [PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text](https://mlsanity.com/paper/1904.09537/) (2019)
- [Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddings](https://mlsanity.com/paper/2002.05969/) (2020)
- [Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases](https://mlsanity.com/paper/2011.07743/) (2020)
- [Large-scale Simple Question Answering with Memory Networks](https://mlsanity.com/paper/1506.02075/) (2015)
- [Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering](https://mlsanity.com/paper/1909.05311/) (2019)
- [UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering](https://mlsanity.com/paper/2012.14610/) (2020)
- [KnowIT VQA: Answering Knowledge-Based Questions about Videos](https://mlsanity.com/paper/1910.10706/) (2019)
- [Question Answering on Freebase via Relation Extraction and Textual Evidence](https://mlsanity.com/paper/1603.00957/) (2016)
- [SimpleQuestions Nearly Solved: A New Upperbound and Baseline Approach](https://mlsanity.com/paper/1804.08798/) (2018)
- [Outlining and Filling: Hierarchical Query Graph Generation for Answering Complex Questions over Knowledge Graphs](https://mlsanity.com/paper/2111.00732/) (2021)
- [Improving Commonsense Question Answering by Graph-based Iterative Retrieval over Multiple Knowledge Sources](https://mlsanity.com/paper/2011.02705/) (2020)
- [LinkNBed: Multi-Graph Representation Learning with Entity Linkage](https://mlsanity.com/paper/1807.08447/) (2018)
- [Crake: Causal-Enhanced Table-Filler for Question Answering over Large Scale Knowledge Base](https://mlsanity.com/paper/2207.03680/) (2022)
- [μKG: A Library for Multi-source Knowledge Graph Embeddings and Applications](https://mlsanity.com/paper/2207.11442/) (2022)

## Built on by (most cited first, 2 of 2)

- [DBRouting: Routing End User Queries to Databases for Answerability](https://mlsanity.com/paper/2501.16220/) (2025)
- [SEAL: Self-Evolving Agentic Learning for Conversational Question Answering over Knowledge Graphs](https://mlsanity.com/paper/2512.04868/) (2025)

## 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.