Knowledge Graph Representation with Jointly Structural and Textual Encoding
Open accessAbstract
The objective of knowledge graph embedding is to encode both entities and relations of knowledge graphs into continuous low-dimensional vector spaces. Previously, most works focused on symbolic representation of knowledge graph with structure information, which can not handle new entities or entities with few facts well. In this paper, we propose a novel deep architecture to utilize both structural and textual information of entities. Specifically, we introduce three neural models to encode the valuable information from text description of entity, among which an attentive model can select related information as needed. Then, a gating mechanism is applied to integrate representations of structure and text into a unified architecture. Experiments show that our models outperform baseline and obtain state-of-the-art results on link prediction and triplet classification tasks.
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?
BERT performs well on many syntactic tasks such as part-of-speech tagging and constituent labeling.
“Tenney et al. [120], Liu et al. [121] found that BERT performs well on many syntactic tasks such as part-of-speech tagging and constituent labeling.”
From Pre-trained models for natural language processing: A survey (2020) · cites this paper as [121]
BERT is not good enough at semantic and fine-grained syntactic tasks, compared with simple syntactic tasks.
“However, BERT is not good enough at semantic and fine-grained syntactic tasks, compared with simple syntactic tasks.”
From Pre-trained models for natural language processing: A survey (2020) · cites this paper as [121]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 41 · Cited by 121
Research works printed but not linked: 2
- Antoine Bordes, Xavier Glorot, Jason Weston, and Yoshua Bengio. A semantic matching energy function for learning with multi-relational data. Machine Learning, 94(2):233-259, 2014.
- Ben Taskar, Vassil Chatalbashev, Daphne Koller, and Carlos Guestrin. Learning struc- tured prediction models: A large margin approach. In Proceedings of the ICML, 2005.
- Authors
- Xu, J., Qiu, X., Chen, K., & Huang, X.
- Affiliations
- Fudan University (CN)
- Corresponding author
- Qiu, Xipeng
- Venue
- Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence
- Published
- 2017-08
- Pages
- 1318-1324
- OpenAlex
- W2558476738
- Cited by
- 121
- References
- 41
- Citations by year
- 2025: 3 · 2024: 12 · 2023: 14 · 2022: 18 · 2021: 14 · 2020: 33 · 2019: 15 · 2018: 11 · 2017: 1
- FWCI
- 7.44
- 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 Natural Science Foundation of China (61532011, 61672162, 16JC1420401)
- Science and Technology Commission of Shanghai Municipality (16JC1420401)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Advanced Graph Neural Networks
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Information Systems › Recommender Systems and Techniques
- Keywords
- knowledge graph embedding, attention mechanism, gating mechanism, link prediction
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
