Context-aware Path Ranking for Knowledge Base Completion
Open accessAbstract
Knowledge base (KB) completion aims to infer missing facts from existing ones in a KB. Among various approaches, path ranking (PR) algorithms have received increasing attention in recent years. PR algorithms enumerate paths between entity-pairs in a KB and use those paths as features to train a model for missing fact prediction. Due to their good performances and high model interpretability, several methods have been proposed. However, most existing methods suffer from scalability (high RAM consumption) and feature explosion (trains on an exponentially large number of features) problems. This paper proposes a Context-aware Path Ranking (C-PR) algorithm to solve these problems by introducing a selective path exploration strategy. C-PR learns global semantics of entities in the KB using word embedding and leverages the knowledge of entity semantics to enumerate contextually relevant paths using bidirectional random walk. Experimental results on three large KBs show that the path features (fewer in number) discovered by C-PR not only improve predictive performance but also are more interpretable than existing baselines.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Unlike prior path ranking studies for KG completion that leverage entities and relations in the KG for path reasoning, our path ranking model additionally considers the relation phrase in the question for ranking.
“Different from those studies using path ranking algorithm for KG completion (Lao et al., 2011;Gardner et al., 2014;Mazumder and Liu, 2017;Das et al., 2018), which leverage the entities and relations in the KG for path reasoning, our path ranking model additionally considers the relation phrase in the question for ranking.”
From Implicit Relation Linking for Question Answering over Knowledge Graph (2022) · cites this paper as Mazumder and Liu, 2017
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Incorporating Vector Space Similarity in Random Walk Inference over Knowledge Bases
Gardner, M., Talukdar, P., Krishnamurthy, J., & Mitchell, T. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1044 · Cited by 189 · see citing works
Flagged first, then by citations
Research works printed but not linked: 24
- Baroni et al., 2014] Marco Baroni, Georgiana Dinu, and Germán Kruszewski. Don't count, predict! a systematic comparison of context-counting vs. context-predicting se- mantic vectors. In ACL, 2014.
- Jonathan Berant, Andrew Chou, Roy Frostig, and Percy Liang. Semantic parsing on freebase from question-answer pairs. In EMNLP. 2013.
- Kurt Bollacker, Colin Evans, Praveen Paritosh, Tim Sturge, and Jamie Taylor. Freebase: a collaboratively created graph database for structuring human knowledge. In SIGMOD, 2008.
- Antoine Bordes, Jason Weston, Ronan Collobert, and Yoshua Bengio. Learning structured em- beddings of knowledge bases. In Conference on artificial intelligence, 2011.
- Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, and Oksana Yakhnenko. Translating embeddings for modeling multi-relational data. In NIPS, 2013.
- Rajarshi Das, Arvind Neelakantan, David Belanger, and Andrew McCallum. Chains of reasoning over entities, relations, and text using recurrent neural net- works. arXiv preprint arXiv:1607.01426, 2016. · arXiv
- Freitas et al., 2014] André Freitas, Joao Carlos Pereira da Silva, Edward Curry, and Paul Buitelaar. A distri- butional semantics approach for selective reasoning on commonsense graph knowledge bases. In International Conference on Applications of Natural Language to Data Bases/Information Systems, 2014.
- Gardner and Mitchell, 2015] Matt Gardner and Tom M Mitchell. Efficient and expressive knowledge base com- pletion using subgraph feature extraction. In EMNLP, 2015.
- Matt Gardner, Partha Pratim Talukdar, Bryan Kisiel, and Tom Mitchell. Improving learning and inference in a large knowledge-base using latent syntactic cues. In ACL, 2013.
- Andrea Gesmundo and Keith Hall. Projecting the knowledge graph to syntactic parsing. In EACL, 2014.
- Jiang et al., 2012] Shangpu Jiang, Daniel Lowd, and Dejing Dou. Learning to refine an automatically extracted knowl- edge base using markov logic. In ICDM, 2012.
- Kyrola, 2013] Aapo Kyrola. Drunkardmob: billions of ran- dom walks on just a pc. In RecSys, 2013.
- Ni Lao, Tom Mitchell, and William W Co- hen. Random walk inference and learning in a large scale knowledge base. In EMNLP, 2011.
- Ni Lao, Einat Minkov, and William W Co- hen. Learning relational features with backward random walks. In ACL, 2015.
- Omer Levy, Yoav Goldberg, and Ido Da- gan. Improving distributional similarity with lessons learned from word embeddings. In TACL, 2015.
- Mikolov et al., 2013a] Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. Efficient estimation of word representations in vector space. In ICLR Workshop, 2013.
- Mikolov et al., 2013b] Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. Distributed repre- sentations of words and phrases and their compositionality. In NIPS, 2013.
- George A Miller. Wordnet: a lexical database for english. In Communications of the ACM, 1995.
- Arvind Neelakantan, Benjamin Roth, and Andrew McCallum. Compositional vector space models for knowledge base completion. In ACL, 2015.
- Maximilian Nickel, Volker Tresp, and Hans-Peter Kriegel. A three-way model for collective learning on multi-relational data. In ICML, 2011.
- Maximilian Nickel, Kevin Murphy, Volker Tresp, and Evgeniy Gabrilovich. A review of re- lational machine learning for knowledge graphs. arXiv preprint arXiv:1503.00759, 2015. · arXiv
- Speer and Havasi, 2012] Robert Speer and Catherine Havasi. Representing general relational knowledge in conceptnet 5. In LREC, 2012.
- Kristina Toutanova. Observed versus la- tent features for knowledge base and text inference. In ACL Workshop on Continuous Vector Space Models and their Compositionality, 2015.
- Quan Wang, Jing Liu, Yuanfei Luo, Bin Wang, and C Lin. Knowledge base completion via coupled path ranking. In ACL, 2016.
Cited by
Sorted by citations
Implicit Relation Linking for Question Answering over Knowledge Graph
Zhao, Y., Huang, J., Hu, W., Chen, Q., Qiu, X., Huo, C., & Ren, W. (2022) · Findings of the Association for Computational Linguistics: ACL 2022 · doi:10.18653/v1/2022.findings-acl.312 · Cited by 5 · see citing works
- Authors
- Mazumder, S., & Liu, B.
- Affiliations
- University of Illinois Chicago (US)
- Venue
- Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence
- Published
- 2017-08
- Pages
- 1195-1201
- OpenAlex
- W2741310710
- Cited by
- 35
- References
- 1
- Citations by year
- 2026: 1 · 2025: 4 · 2024: 7 · 2023: 5 · 2022: 5 · 2021: 4 · 2020: 3 · 2019: 5 · 2018: 1
- FWCI
- 1.12
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- International Joint Conference on Artificial Intelligence (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (1650900, 1407927)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Advanced Graph Neural Networks
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Semantic Web and Ontologies
- Keywords
- knowledge base completion, path ranking, missing fact prediction, word embeddings, scalability, interpretability
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
