Complex Knowledge Base Question Answering: A Survey
Open accessThe DOI matches its Crossref record; 28 of the 28 references it cites were found in a registry or an index.
Abstract
Knowledge base question answering (KBQA) aims to answer a question over a knowledge base (KB). Early studies mainly focused on answering simple questions over KBs and achieved great success. However, their performances on complex questions are still far from satisfactory. Therefore, in recent years, researchers propose a large number of novel methods, which looked into the challenges of answering complex questions. In this survey, we review recent advances in KBQA with the focus on solving complex questions, which usually contain multiple subjects, express compound relations, or involve numerical operations. In detail, we begin with introducing the complex KBQA task and relevant background. Then, we present two mainstream categories of methods for complex KBQA, namely semantic parsing-based (SP-based) methods and information retrieval-based (IR-based) methods. Specifically, we illustrate their procedures with flow designs and discuss their difference and similarity. Next, we summarize the challenges that these two categories of methods encounter when answering complex questions, and explicate advanced solutions as well as techniques used in existing work. After that, we discuss the potential impact of pre-trained language models (PLMs) on complex KBQA. To help readers catch up with SOTA methods, we also provide a comprehensive evaluation and resource about complex KBQA task. Finally, we conclude and discuss several promising directions related to complex KBQA for future research.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
On Information and Sufficiency
Kullback, S., & Leibler, R. A. (1951) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177729694 · Cited by 20,193
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019) · arXiv · doi:10.48550/arxiv.1907.11692 · Cited by 16,515
WordNet: a lexical database for English
Miller, G. A. (1995) · Communications of the ACM · doi:10.1145/219717.219748 · Cited by 14,015 · cited 1×
“YAGO [21] takes Wikipedia and WordNet [22] as the knowledge resources and covers taxonomy of more general concepts.”
BackgroundExploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Finn, C., Abbeel, P., & Levine, S. (2017) · arXiv · doi:10.48550/arxiv.1703.03400 · Cited by 8,512 · cited 1×
“Specifically, they employed a meta learning-based framework [109] that aims to learn a general model which can easily adapt to question types with few sources.”
MethodFreebase: a collaboratively created graph database for structuring human knowledge
Bollacker, K., Evans, C., Paritosh, P., Sturge, T., & Taylor, J. (2008) · Proceedings of the 2008 ACM SIGMOD international conference on Management of data · doi:10.1145/1376616.1376746 · Cited by 4,852
Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks
Tai, K. S., Socher, R., & Manning, C. D. (2015) · Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.3115/v1/p15-1150 · Cited by 3,081
On the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676
Complex Embeddings for Simple Link Prediction
Trouillon, T., Welbl, J., Riedel, S., Gaussier, É., & Bouchard, G. (2016) · arXiv · doi:10.48550/arxiv.1606.06357 · Cited by 2,100
Feng, Y., You, H., Zhang, Z., Ji, R., & Gao, Y. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33013558 · Cited by 1,895
CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning
Johnson, J., Hariharan, B., van der Maaten, L., Fei-Fei, L., Zitnick, C. L., & Girshick, R. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.215 · Cited by 1,781
ERNIE: Enhanced Language Representation with Informative Entities
Zhang, Z., Han, X., Liu, Z., Jiang, X., Sun, M., & Liu, Q. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1139 · Cited by 1,482 · cited 1×
“Similar ideas were also adopted in knowledge-enhanced language model pre-training [98], [99].”
ResultSukhbaatar, S., Szlam, A., Weston, J., & Fergus, R. (2015) · arXiv · doi:10.48550/arxiv.1503.08895 · Cited by 1,345
How Can We Know What Language Models Know?
Jiang, Z., Xu, F. F., Araki, J., & Neubig, G. (2020) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00324 · Cited by 1,002
Local Graph Partitioning using PageRank Vectors
Andersen, R., Chung, F., & Lang, K. (2006) · 2006 47th Annual IEEE Symposium on Foundations of Computer Science (FOCS'06) · doi:10.1109/focs.2006.44 · Cited by 967
Representation Learning of Knowledge Graphs with Entity Descriptions
Xie, R., Liu, Z., Jia, J., Luan, H., & Sun, M. (2016) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v30i1.10329 · Cited by 725
Knowledge Enhanced Contextual Word Representations
Peters, M. E., Neumann, M., Logan, R., Schwartz, R., Joshi, V., Singh, S., & Smith, N. A. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1005 · Cited by 661 · cited 1×
“Similar ideas were also adopted in knowledge-enhanced language model pre-training [98], [99].”
ResultLarge-scale Simple Question Answering with Memory Networks
Bordes, A., Usunier, N., Chopra, S., & Weston, J. (2015) · arXiv · doi:10.48550/arxiv.1506.02075 · Cited by 528 · cited 2×
“The two categories of methods are commonly known as semantic parsing-based (SP-based) methods and information retrieval-based (IR-based) methods in prior work [6], [7], [10], [13].”
BackgroundMethodThe Web as a Knowledge-Base for Answering Complex Questions
Talmor, A., & Berant, J. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1059 · Cited by 520 · cited 2×
“As decomposing questions costs manual efforts, they reduced human annotation and identify the composition plan through an augmented pointer network [81].”
MethodMeasuring Compositional Generalization: A Comprehensive Method on Realistic Data
Keysers, D., Schärli, N., Scales, N., Buisman, H., Furrer, D., Kashubin, S., Momchev, N., Sinopalnikov, D., Stafiniak, L., Tihon, T., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.09713 · Cited by 264
LC-QuAD: A Corpus for Complex Question Answering over Knowledge Graphs
Trivedi, P., Maheshwari, G., Dubey, M., & Lehmann, J. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-68204-4_22 · Cited by 261
A Survey of Knowledge-enhanced Text Generation
Yu, W., Zhu, C., Li, Z., Hu, Z., Wang, Q., Ji, H., & Jiang, M. (2022) · ACM Computing Surveys · doi:10.1145/3512467 · Cited by 257
Neural Generative Question Answering
Yin, J., Jiang, X., Lu, Z., Shang, L., Li, H., & Li, X. (2016) · Proceedings of the Workshop on Human-Computer Question Answering · doi:10.18653/v1/w16-0106 · Cited by 186
Hierarchical Query Graph Generation for Complex Question Answering over Knowledge Graph
Qiu, Y., Zhang, K., Wang, Y., Jin, X., Bai, L., Guan, S., & Cheng, X. (2020) · Proceedings of the 29th ACM International Conference on Information & Knowledge Management · doi:10.1145/3340531.3411888 · Cited by 52 · cited 3×
“Recently, Qiu et al. [67] formulated query graph generation as a hierarchical decision problem, and proposed an option-based hierarchical framework to provide intermediate rewards for low-level agents.”
BackgroundMethodReasoning Over Virtual Knowledge Bases With Open Predicate Relations
Sun, H., Verga, P., Dhingra, B., Salakhutdinov, R., & Cohen, W. W. (2021) · arXiv · doi:10.48550/arxiv.2102.07043 · Cited by 14
Message Passing for Complex Question Answering over Knowledge Graphs
Vakulenko, S., Fernandez Garcia, J. D., Polleres, A., de Rijke, M., & Cochez, M. (2019) · Proceedings of the 28th ACM International Conference on Information and Knowledge Management · doi:10.1145/3357384.3358026 · Cited by 14 · cited 1×
“LC-QuAD [117] DBpedia 5,000 Yes Yes Yes Yes 75:0~ [58] 74:8~ [59] 71:8~ [118] 33:0~ [119] -”
Cited by
HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models
Li, J., Cheng, X., Zhao, W. X., Nie, J.-Y., & Wen, J.-R. (2023) · arXiv · doi:10.48550/arxiv.2305.11747 · Cited by 340
Self-citationHaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models
Li, J., Cheng, X., Zhao, X., Nie, J.-Y., & Wen, J.-R. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.397 · Cited by 343
Self-citationGraph Retrieval-Augmented Generation: A Survey
Peng, B., Zhu, Y., Liu, Y., Bo, X., Shi, H., Hong, C., Zhang, Y., & Tang, S. (2026) · ACM Transactions on Information Systems · doi:10.1145/3777378 · Cited by 206
“Developing advanced retrieval algorithms and scalable infrastructure is essential to address this issue, ensuring that the system can manage the extensive data volume while maintaining high performance and accuracy in entity retrieval.”
TempoQR: Temporal Question Reasoning over Knowledge Graphs
Mavromatis, C., Subramanyam, P. L., Ioannidis, V. N., Adeshina, A., Howard, P. R., Grinberg, T., Hakim, N., & Karypis, G. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i5.20526 · Cited by 16
Decider: A Dual-System Rule-Controllable Decoding Framework for Language Generation
Xu, C., Lan, T., Ji, Y., Yu, C., Wang, W., Gao, J., Dong, Q., Qian, K., Li, P., Bi, W., et al. (2025) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2025.3554819 · Cited by 2
“C ONTROLLABLE natural language generation [1], [2], [3] aims to generate natural sentences that satisfy specific conditions, such as sentiment [4], [5], topic [6], [7], [8], [9], [10] and keywords [11], [12], [13].”
Metadata
- Authors
- Lan, Y., He, G., Jiang, J., Jiang, J., Zhao, W. X., & Wen, J.-R.
- Venue
- IEEE Transactions on Knowledge and Data Engineering
- Published
- 2023-11-01
- Volume
- 35
- Issue
- 11
- Pages
- 11196-11215
- ISSN
- 1041-4347 (ISSN-L)
- 1558-2191
- 2326-3865
- OpenAlex
- W4312634749
- Cited by
- 117
- References
- 28
- FWCI
- 7.43
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.