Knowledge Graph and Text Jointly Embedding
Open accessThe DOI matches its Crossref record; 20 of the 22 references it cites were found in a registry or an index.
Abstract
We examine the embedding approach to reason new relational facts from a largescale knowledge graph and a text corpus.We propose a novel method of jointly embedding entities and words into the same continuous vector space.The embedding process attempts to preserve the relations between entities in the knowledge graph and the concurrences of words in the text corpus.Entity names and Wikipedia anchors are utilized to align the embeddings of entities and words in the same space.Large scale experiments on Freebase and a Wikipedia/NY Times corpus show that jointly embedding brings promising improvement in the accuracy of predicting facts, compared to separately embedding knowledge graphs and text.Particularly, jointly embedding enables the prediction of facts containing entities out of the knowledge graph, which cannot be handled by previous embedding methods.At the same time, concerning the quality of the word embeddings, experiments on the analogical reasoning task show that jointly embedding is comparable to or slightly better than word2vec (Skip-Gram).
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.
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?
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“Inspired by these work, Rubinstein et al. [118] found that distributional word representations are good at predicting taxonomic properties (e.g., dog is an animal) but fail to learn attributive properties (e.g., swan is white).”
From Pre-trained models for natural language processing: A survey (2020) · cites this paper as [118]
Experimental — accuracy not yet measured
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
Efficient Estimation of Word Representations in Vector Space
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1301.3781 · Cited by 26,568 · cited 16×
“NEG guarantees that maximizing Eq.”
BackgroundMethodInfluentialDistributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533
WordNet: a lexical database for English
Miller, G. A. (1995) · Communications of the ACM · doi:10.1145/219717.219748 · Cited by 14,015
(2013) · Cited by 5,726
Natural Language Processing (almost) from Scratch
Collobert, R., Weston, J., Bottou, L., Karlen, M., Kavukcuoglu, K., & Kuksa, P. P. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1103.0398 · Cited by 4,962 · cited 1×
“Generally, word embeddings are learned from a given text corpus without supervision by predicting the context of each word or predicting the current word given its context (Bengio et al., 2003; Collobert et al., 2011; Mikolov et al., 2013a; Mikolov et al., 2013b).”
BackgroundFreebase: 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 · cited 12×
“Knowledge graphs such as Freebase (Bollacker et al., 2008) and WordNet (Miller, 1995) have become important resources for many AI & NLP applications such as Q & A.”
BackgroundInfluentialKnowledge Graph Embedding by Translating on Hyperplanes
Wang, Z., Zhang, J., Feng, J., & Chen, Z. (2014) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v28i1.8870 · Cited by 3,915 · cited 2×
“Recently, targeting knowledge graph completion, a promising paradigm of embedding was proposed, which is able to reason new facts only from the knowledge graph (Bordes et al., 2011; Bordes et al., 2013; Socher et al., 2013; Wang et al., 2014).”
BackgroundSelf-citationDistant supervision for relation extraction without labeled data
Mintz, M., Bills, S., Snow, R., & Jurafsky, D. (2009) · Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 2 - ACL-IJCNLP '09 · doi:10.3115/1690219.1690287 · Cited by 2,752 · cited 3×
“For (Mintz et al., 2009), we use the implementation in (Surdeanu et al., 2012) 4 .”
BackgroundMethodA neural probabilistic language model
BengioYoshua, DucharmeRéjean, VincentPascal, & JanvinChristian (2003) · Journal of Machine Learning Research · doi:10.5555/944919.944966 · Cited by 2,644
Reasoning With Neural Tensor Networks for Knowledge Base Completion
Socher, R., Chen, D., Manning, C. D., & Ng, A. Y. (2013) · neural information processing systems · Cited by 2,228
Research works printed but not linked: 1
- Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Cor- rado, and Jeff Dean. 2013b. Distributed representa- tions of words and phrases and their compositional- ity. In Advances in Neural Information Processing Systems 26, pages 3111-3119.
Cited by
Items 201–300 of 406
Ad hoc retrieval via entity linking and semantic similarity
Ensan, F., & Du, W. (2018) · Knowledge and Information Systems · doi:10.1007/s10115-018-1190-1 · Cited by 12
“We would like to complement our work with exploring other semantic relatedness systems, especially new methods in finding similarities between entities using embedding techniques [18,49].”
MethodCoRelatE: Learning the correlation in multi-fold relations for knowledge graph embedding
Huang, Y., Sun, H., Xu, K., Lu, S., Wang, T., & Zhang, X. (2020) · Knowledge-Based Systems · doi:10.1016/j.knosys.2020.106601 · Cited by 13
Liu, Z., Lin, Y., & Sun, M. (2020) · Springer eBooks · doi:10.1007/978-981-15-5573-2_2 · Cited by 12
“Some prelimi-nary explorations have attempted [59, 60] to utilize heterogeneous knowledge for learning better word representations, and these explorations indicate that utilizing more knowledge is a promising direction toward enhancing word representations.”
BackgroundMachine Learning with World Knowledge: The Position and SurveyPreprint
Song, Y., & Roth, D. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.02908 · Cited by 14
“Text classification [226], text clustering [225], [224], [227] Text classification [201], [124], relation clas-sification [228], relation extraction [220], entity disambiguation [56], word analogy [228], recommendation system [244] where the concept vector is considered as a feature vector to generate…”
BackgroundInfluentialTowards the Web of Embeddings: Integrating multiple knowledge graph embedding spaces with FedCoder
Baumgartner, M., Dell’Aglio, D., Paulheim, H., & Bernstein, A. (2022) · Journal of Web Semantics · doi:10.1016/j.websem.2022.100741 · Cited by 12
“Wang et al. [20] learn an embedding from KG triples and entity labels.”
BackgroundYe, Q., Yang, R., Cheng, C.-L., Lin, P., & Lan, Y. (2023) · Evidence-based Complementary and Alternative Medicine · doi:10.1155/2023/2088698 · Cited by 12
Probabilistic Belief Embedding for Knowledge Base CompletionPreprint
Fan, M., Zhou, Q., Abel, A. K., Zheng, T. F., & Grishman, R. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1505.02433 · Cited by 11
A Structural Representation Learning for Multi-relational Networks
Liu, L., Li, X., Cheung, W. K., & Xu, C. (2017) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2017/565 · Cited by 10
Bauer, L., Deng, L., & Bansal, M. (2021) · Workshop on Knowledge Extraction and Integration for Deep Learning Architectures: Deep Learning Inside Out (DeeLIO) · doi:10.18653/v1/2021.deelio-1.7 · Cited by 10
“Wang et al. (2014) used entity names and Wikipedia anchors to align the embeddings of entities and words in the same space.”
MethodEnhancing Knowledge Graph Embedding from a Logical Perspective
Du, J., Qi, K., Wan, H., Peng, B., Lu, S., & Shen, Y. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-70682-5_15 · Cited by 10
“One kind of text information namely entity names and their corresponding Wikipedia anchors is used in the probabilistic TransE (pTransE) method [21] to embed both triples and words.”
MethodAligning Knowledge Base and Document Embedding Models Using Regularized Multi-Task Learning
Baumgartner, M., Zhang, W., Paudel, B., Dell’Aglio, D., Chen, H., & Bernstein, A. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00671-6_2 · Cited by 11
“[21] and [16] jointly learn embeddings of words and entities, by using an alignment loss function based on the cooccurrence of entity and words in its descriptions, or Wikipedia anchors, respectively.”
Multi-source Knowledge Fusion: A Survey
Zhao, X., Jia, Y., Li, A., Jiang, R., Xie, H., Song, Y., & Han, W. (2019) · IEEE International Conference on Data Science in Cyberspace · doi:10.1109/dsc.2019.00026 · Cited by 12
Entity Alignment Across Knowledge Graphs Based on Representative Relations Selection
Zhang, Y., Liu, L., Fu, S., & Zhong, F. (2018) · International Conference on Systems and Informatics (ICSAI) · doi:10.1109/icsai.2018.8599288 · Cited by 12
“Translation based methods [7], [11], [12], [13] were widely used for this task.”
BackgroundMethodWebBrain: Joint Neural Learning of Large-Scale Commonsense Knowledge
Chen, J., Tandon, N., Hariman, C. D., & de Melo, G. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46523-4_7 · Cited by 11
Knowledge-Enhanced Prompt Learning for Few-Shot Text Classification
Liu, J., & Yang, L. (2024) · Big Data and Cognitive Computing · doi:10.3390/bdcc8040043 · Cited by 13
“The simplest knowledge injection method is just combining entity embedding with the word embedding of pre-trained models [35], but the problem with this method is that embedding obtained from multiple sources cannot be aligned.”
MethodSemantic Information Extraction for Improved Word Embeddings
Chen, J., & de Melo, G. (2015) · Workshop on Vector Space Modeling for Natural Language Processing (VSM-NLP) · doi:10.3115/v1/w15-1523 · Cited by 10
“Wang et al. (2014) train embeddings jointly on text and on Freebase, a well-known large knowledge base.”
BackgroundAccelerating Entity Lookups in Knowledge Graphs Through Embeddings
Abuoda, G., Thirumuruganathan, S., & Aboulnaga, A. (2022) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde53745.2022.00088 · Cited by 9
“One class of work accomplishes this by optimizing an objective function that combines entity and text information to learn joint embeddings [26], [28].”
BackgroundImproving entity linking with two adaptive features
Zhang, H., Chen, Q., & Zhang, W. (2022) · Frontiers of Information Technology & Electronic Engineering · doi:10.1631/fitee.2100495 · Cited by 9
“The joint model framework (Wang Z et al., 2014) and alignment technology (Zhong et al., 2015) have been used to design a feature that could present correlations between significant words around a mention and its candidates (Fang W et al., 2016).”
MethodOERL: Enhanced Representation Learning via Open Knowledge Graphs
Li, Q., Wang, D., Feng, S., Song, K., Zhang, Y., & Yu, G. (2022) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2022.3218850 · Cited by 9
“Wang et al. [26] align the KG with an auxiliary textual corpus and combine the representation learning of KGs with that of words to better utilize external textual features.”
BackgroundSummers-Stay, D. A., Voss, C. R., & Cassidy, T. (2016) · Biologically Inspired Cognitive Architectures · doi:10.1016/j.bica.2016.03.002 · Cited by 10
GCP: Graph Encoder With Content-Planning for Sentence Generation From Knowledge Bases
Trisedya, B. D., Qi, J., Wang, W., & Zhang, R. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3118703 · Cited by 10
“Sharing representation is the most common technique for the joint learning [32], [33].”
MethodSpatio-temporal knowledge embedding method considering the lifecycle of geographical entities
Zhao, X., Zhang, J., Cao, Y., Yang, F., Yang, Z., & Fan, X. (2024) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2024.103967 · Cited by 10
Self-citationSubGram: Extending Skip-Gram Word Representation with Substrings
Kocmi, T., & Bojar, O. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-45510-5_21 · Cited by 8
“Vector representations of words learned using neural networks (NN) have proven helpful in many algorithms for image annotation [1] or [2], language modeling [3], [4] and [5] or other natural language processing (NLP) tasks [6] or [7].”
BackgroundHe, G., Liang, Y., Chen, Y., Yang, W. E., Liu, J. S., Yang, M. Q., & Guan, R. (2018) · BMC Systems Biology · doi:10.1186/s12918-018-0640-4 · Cited by 8
“Recently, plenty of NLP tasks, such as knowledge graph completion and text mining have introduced word2vec model [33 – 35].”
BackgroundRepresentation Learning of Knowledge Graphs via Fine-Grained Relation Description Combinations
He, M., Du, X., & Wang, B. (2019) · IEEE Access · doi:10.1109/access.2019.2901544 · Cited by 10
“Reference [22] makes an attempt to project words and entities into a same continuous vector space jointly by alignment models in Wikipedia anchors and entity names.”
BackgroundMethodModeling of complex internal logic for knowledge base completion
Wang, H., Jiang, S., & Yu, Z. (2020) · Applied Intelligence · doi:10.1007/s10489-020-01734-z · Cited by 8
“First, integrating the semantic information into the PTransE, and strengthens the credibility scores of the positive and negative triples with the semantic gap, which not only makes the model converge faster, but also can obtain the knowledge representation of the fusion semantic information; and then the triple repre…”
InfluentialLearning company embeddings from annual reports for fine-grained industry characterization
Ito, T., Camacho-Collados, J., Sakaji, H., & Schockaert, S. (2020) · ORCA Online Research @Cardiff (Cardiff University) · Cited by 23
Ursuleanu, T. F., Luca, A. R., Gheorghe, L., Grigorovici, R., Iancu, S., Hlusneac, M., Preda, C., & Grigorovici, A. (2021) · E-Health Telecommunication Systems and Networks · doi:10.4236/etsn.2021.102003 · Cited by 8
“The graphs of medical knowledge describing, the relationship between different types of knowledge, the relationship between different diseases, the relationship between medical datasets and a type of medical data, help deep learning models work [147].”
BackgroundProbabilistic Belief Embedding for Large-Scale Knowledge Population
Fan, M., Zhou, Q., Abel, A. K., Zheng, T. F., & Grishman, R. (2016) · Cognitive Computation · doi:10.1007/s12559-016-9425-5 · Cited by 8
“[Wang et al. 2014a] and Fan et al.”
Remembering what you said: Semantic personalized memory for personal digital assistants
Agarwal, V., Khan, O. Z., & Sarikaya, R. (2017) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2017.7953275 · Cited by 8
“Word embeddings improve accuracy of disambiguation [21, 22] and KGs have been used to construct word embeddings [23, 24, 25, 26].”
MethodBridging the gap between linked open data-based recommender systems and distributed representations
Basile, P., Greco, C., Suglia, A., & Semeraro, G. M. (2019) · Information Systems · doi:10.1016/j.is.2019.07.001 · Cited by 8
“Recently, vector space embeddings of knowledge graphs have gained considerable attention [9] and have been applied to several tasks such as link predic-20 tion, entity disambiguation, extraction of taxonomies and question answering [10, 11, 12, 13].”
BackgroundRevisiting Text and Knowledge Graph Joint Embeddings: The Amount of Shared Information Matters!
Rosso, P., Yang, D., & Cudré-Mauroux, P. (2019) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata47090.2019.9005462 · Cited by 8
“In this paper, we adopt two common types of anchors, 1) entity names appeared in text and 2) entityassociated Wikipedia pages, which are widely used in the current literature [13], [16].”
BackgroundMethodResultInfluentialA Survey of Task-Oriented Knowledge Graph Reasoning: Status, Applications, and ProspectsPreprint
Niu, G., Li, B., & Lin, Y. (2025) · doi:10.36227/techrxiv.174961563.32605293/v1 · Cited by 10
Improving Clinical Diagnosis Inference through Integration of Structured and Unstructured Knowledge
Yuan, L., An, Y., & Hasan, S. A. (2017) · doi:10.18653/v1/w17-1904 · Cited by 10
“To improve word embedding models, previous works have also successfully leveraged structured KBs (Bordes et al., 2011; Weston et al., 2013; Wang et al., 2014; Zhou et al., 2015; Liu et al., 2015).”
MethodMulti-lingual Entity Discovery and Linking
Sil, A., Ji, H., Roth, D., & Cucerzan, S.-P. (2018) · doi:10.18653/v1/p18-5008 · Cited by 11
Wu, X., Cai, Y., Li, Q., Xu, J., & Leung, H.-F. (2020) · World Wide Web · doi:10.1007/s11280-019-00757-y · Cited by 7
“Word embedding, which first proposedd in Rumelhart et al. [34], has received a significant amount of interest recently, RCM [53], knowledge embedding [44], SensEmbed [10] focus on leveraging external lexical resources to further improve the word embedding.”
BackgroundA Knowledge Graph Embedding Framework With Triple Semantics
Wang, Y., Liang, H., Zheng, K., Yang, J., Zeng, L., Gong, Q., Li, S., & Zhou, S. (2023) · IEEE Access · doi:10.1109/access.2022.3227714 · Cited by 7
“Wang et al. [52] proposed a novel method of jointly embedding knowledge graphs and a text corpus so that entities and words/phrases are represented in the same vector space.”
MethodZero-Shot Embedding for Unseen Entities in Knowledge Graph
Zhao, Y., Gao, S., Gallinari, P., & Guo, J. H. (2017) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2016edp7446 · Cited by 9
Knowledge Graph Embedding Translation Based on Constraints.
Wu, Y., Pan, J., Lü, P., Lin, K.-B., & Yu, X. (2017) · J. Inf. Hiding Multim. Signal Process. · Cited by 7
Knowledge Graph Essentials and Key Technologies
Gurin, V., Викторович, К. Е., Gavrilenko, Y., Saada, D., Ilyushin, E., & Chizhov, I. V. (2019) · Sovremennye informacionnye tehnologii i IT-obrazovanie. · doi:10.25559/sitito.15.201904.932-944 · Cited by 8
“Many follow-up works like TransH [43], [2], and TransR [29], proposed advanced methods of translation by introducing different embedding spaces.”
MethodConnecting emerging relationships from news via tensor factorization
Zhang, J., Lu, C.-T., Cao, B., Chang, Y., & Yu, P. S. (2017) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2017.8258048 · Cited by 7
“Furthermore, some work tries to embed the KG and the texts jointly [3, 18].”
BackgroundMethodInfluentialSelf-citationDing, J., Ma, S., Jia, W., & Guo, M. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-96890-2_31 · Cited by 8
“There are several methods [20,23,26] representing KGs with textual information.”
BackgroundMethodLiu, Z., Lin, Y., & Sun, M. (2020) · Springer eBooks · doi:10.1007/978-981-15-5573-2_4 · Cited by 8
Knowledge Semantic Representation: A Generative Model for Interpretable Knowledge Graph Embedding.Preprint
Xiao, H., Huang, M., & Zhu, X. (2016) · arXiv (Cornell University) · Cited by 8
Word and Document Embeddings based on Neural Network ApproachesPreprint
Lai, S. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.05962 · Cited by 10
“[122] Zhen Wang, Jianwen Zhang, Jianlin Feng, and Zheng Chen.”
BackgroundSemantically Enhanced Models for Commonsense Knowledge Acquisition
Alhussien, I., Cambria, E., & NengSheng, Z. (2018) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw.2018.00146 · Cited by 6
MUKG: Unifying Multi-Task and Knowledge Graph Method for Recommender System
Sun, J., & Shagar, M. M. B. (2020) · International Conference on Image Processing and Machine Vision (IPMV) · doi:10.1145/3421558.3421561 · Cited by 6
“The KG methods can be incorporated into the following two kinds: (1) Translational distance features operate distance rating functions while trying to learn entities and interaction representation, like TransE [8], TransH [9], and TransR [10].”
MethodAn Adversarial Transfer Network for Knowledge Representation Learning
Wang, H., Li, S., & Pan, R. (2021) · International World Wide Web Conference (WWW) · doi:10.1145/3442381.3450064 · Cited by 7
“Some information obtained in unsupervised ways is also useful, including context words [35], relation paths [9], and even logical rules [32].”
BackgroundTopic-Based Embeddings for Learning from Large Knowledge Graphs
Hu, C., Rai, P., & Carin, L. (2016) · International Conference on Artificial Intelligence and Statistics · Cited by 13
Siamese Pre-Trained Transformer Encoder for Knowledge Base Completion
Li, M., Wang, B., & Jiang, J. B. (2021) · Neural Processing Letters · doi:10.1007/s11063-021-10586-8 · Cited by 7
“Instead of considering only the structured knowledge of the graph, textual encoding approaches [23,28–30] propose to incorporate the textual information with structured knowledge for knowledge base completion.”
MethodKIMedQA: towards building knowledge-enhanced medical QA models
Zafar, A., Sahoo, S. K., Varshney, D., Das, A., & Ekbal, A. (2024) · Journal of Intelligent Information Systems · doi:10.1007/s10844-024-00844-1 · Cited by 11
“Wang et al. (2014) proposed a novel approach based on the word2vec Mikolov et al. (2013) technique for infusing embedding entities and words, while Toutanova et al. (2015) developed a model that optimized entity, knowledge base, and textual relation representations to preserve textual relations in…”
Word Embedding as Maximum A Posteriori Estimation
Jameel, S., Fu, Z., Shi, B., Lam, W. P., & Schockaert, S. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33016562 · Cited by 6
“2017), (Ensan 2018), knowledge base completion (Yang, Tang, and Cohen 2016), (Wang et al. 2014), (Zhong et al.”
BackgroundIncorporating Description Embeddings into Medical Knowledge Graphs Representation Learning
Sun, X., Man, Y., Zhao, Y., He, J., & Liu, N. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-15127-0_19 · Cited by 7
Cross-lingual Joint Entity and Word Embedding to Improve Entity Linking and Parallel Sentence Mining
Pan, X., Gowda, T., Ji, H., May, J., & Miller, S. (2019) · Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo) · doi:10.18653/v1/d19-6107 · Cited by 7
“Similar to previous work (Wang et al., 2014; Tsai and Roth, 2016; Ya-mada et al., 2016), we replace each anchor link with its corresponding entity title, and thus treat each entity title as a unique word.”
ResultStructural and Textual Information Fusion for Symptom and Disease Representation Learning
Zhao, S., Jiang, M., Qin, B., Liu, T., Zhai, C., & Wang, F. (2020) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2020.3039469 · Cited by 6
W-KG2Vec: a weighted text-enhanced meta-path-based knowledge graph embedding for similarity search
Do, P., & Pham, P. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-06252-8 · Cited by 10
“Recently, with successes of auto-encoding approach, such as GPT [36] and BERT [27], in natural textual data processing, several studies have been adopted these techniques to leverage the performance of KG embedding task in the rich-textual context, such as KG-BERT [42] and K-BERT [41].”
MethodEffective FAQ Retrieval and Question Matching Tasks with Unsupervised Knowledge Injection
Tseng, W.-T., Hsu, Y.-C., & Chen, B. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-83527-9_11 · Cited by 6
TransFusion: Multi-Modal Fusion for Video Tag Inference via Translation-based Knowledge Embedding
Jin, D., Qi, Z., Luo, Y., & Shan, Y. (2021) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3474085.3481535 · Cited by 7
Discovering Supply Chain Links with Augmented IntelligencePreprint
Gopal, A., & Chang, C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.01878 · Cited by 6
“For textual descriptions, methods vary from using word embeddings [61, 70, 71] to convolutions [73] to attention [2, 74].”
MethodWord Embeddings for Entity-Annotated Texts
Almasian, S., Spitz, A., & Gertz, M. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-15712-8_20 · Cited by 5
“d embedding models specic to named entity linkage by using knowledge bases. Embedding entities in a knowledge graph has also been studied for relational fact extraction and knowledge base completion [41,44]. All of these methods depend on knowledge bases as an external source of information, and often train entity and…”
BackgroundSuo, X., Guo, B., Shen, Y., Chen, Y., & Wang, W. (2023) · Information Processing & Management · doi:10.1016/j.ipm.2023.103411 · Cited by 5
A study of concept similarity in Wikidata
Ilievski, F., Shenoy, K., Chalupsky, H., Klein, N., & Szekely, P. A. (2024) · Semantic Web · doi:10.3233/sw-233520 · Cited by 7
“Multiple ways to use ontologies and distributional models together exist, including joint approach [45, 46], injection [29, 47], and embedding combination [48].”
MethodType Vector Representations from Text: An Empirical Analysis.
Bianchi, F., Soto, M., Palmonari, M., & Cutrona, V. (2018) · Cited by 5
The Role of Knowledge in Determining Identity of Long-Tail Entities
Ilievski, F., Hovy, E. H., Vossen, P. T. J. M., Stefan Schlobach, A., & Xie, Q. (2020) · Journal of Web Semantics · doi:10.1016/j.websem.2020.100565 · Cited by 5
Entity Disambiguation Leveraging Multi-Perspective Attention
Wang, C., Sun, X., Yu, H., & Zhang, W. (2019) · IEEE Access · doi:10.1109/access.2019.2933644 · Cited by 5
“Some researchers [34], [38], [39] argue that jointly embedding words and entities in the same continuous space can improve the performance of entity disambiguation system.”
BackgroundMethodInterpretable Complex Question Answering
Chakrabarti, S. (2020) · International World Wide Web Conference (WWW) · doi:10.1145/3366423.3380764 · Cited by 5
“Concurrent with developments in QA, continuous (embedding) representations of words [11, 13], types [17], entities and relations [20, 22] were developed.”
BackgroundWorld Knowledge Representation
Liu, Z., Lin, Y., & Sun, M. (2020) · Springer eBooks · doi:10.1007/978-981-15-5573-2_7 · Cited by 6
Exploiting knowledge graph and text for ranking entity types
Rahman, M. M., & Takasu, A. (2020) · ACM SIGAPP Applied Computing Review · doi:10.1145/3429204.3429207 · Cited by 6
HRS: Hybrid Recommendation System based on Attention Mechanism and Knowledge Graph Embedding
Dong, C., Ju, X., & Ma, Y. (2021) · IEEE/WIC/ACM International Conference on Web Intelligence · doi:10.1145/3498851.3498987 · Cited by 5
“There are two categories about KGE methods: (1) Translational distance models exploit distance-based scoring functions when learning representations of entities and relations, such as TransE [1], TransH [29], and TransR [10]; (2) Semantic matching modelsmeasure plausibility of knowledge triples bymatching latent seman…”
MethodJoint Embedding of Query and Ad by Leveraging Implicit Feedback
Lee, S.-J., & Hu, Y. (2015) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d15-1054 · Cited by 6
“Joint embedding has also been applied to question answering (Wang et al., 2014) and semantic understanding (Yang et al., 2014).”
BackgroundEntity mention aware document representation
Dai, H., Tang, S., Wu, F. Q., & Zhuang, Y. (2017) · Information Sciences · doi:10.1016/j.ins.2017.11.032 · Cited by 5
Joint Knowledge Graph and User Preference for Explainable Recommendation
Wang, Z., Li, Y., Fang, L., & Chen, P. (2019) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/iccc47050.2019.9064099 · Cited by 5
“There are mainly two methods for knowledge graph embedding: translation distance based methods such as TransE [11], TransH [12]; semantic matching models such as RESCAL [13], ANALOGY [14].”
MethodSelf-citationExpeditious Generation of Knowledge Graph EmbeddingsPreprint
Soru, T., Ruberto, S., Moussallem, D., Valdestilhas, A., Bigerl, A., Marx, E., & Esteves, D. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.07828 · Cited by 6
“An effort to jointly embed structured and unstructured data (such as text) was proposed in [19].”
BackgroundMethodInfluentialRETRO: Relation Retrofitting For In-Database Machine Learning on Textual DataPreprint
Günther, M., Thiele, M., & Lehner, W. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.12674 · Cited by 5
“However, these joined learning approaches [35–38] can hardly be adapted to the relations of text values in relational database systems.”
BackgroundSemantic Triple Encoder for Fast Open-Set Link Prediction.Preprint
Wang, B., Shen, T., Long, G., Zhou, T., & Chang, Y. (2020) · arXiv (Cornell University) · Cited by 6
Advancing Chatbot Conversations: A Review of Knowledge Update Approaches
Costa, L. A. L. F. D., Melchiades, M. B., Girelli, V. S., Colombelli, F., de Araújo, D. A., Rigo, S. J., Ramos, G. D. O., da Costa, C. A., Righi, R. D. R., & Barbosa, J. L. V. (2024) · Journal of the Brazilian Computer Society · doi:10.5753/jbcs.2024.2882 · Cited by 4
Wu, G., Wang, M., & Wang, F. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.112163 · Cited by 4
Joint Representations of Knowledge Graphs and Textual Information via Reference Sentences
Ji, Z., Lei, Z., Shen, T., & Zhang, J. (2020) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2019edp7229 · Cited by 6
“Wherein, Wang [16] associated the knowledge graph and textual information with alignment.”
BackgroundMethodInfluentialSelf-citationFast and Slow Thinking: A Two-Step Schema-Aware Approach for Instance Completion in Knowledge Graphs
Yang, D., Qu, B., Rosso, P., & Cudré-Mauroux, P. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2023.3304137 · Cited by 5
“On the other hand, some other techniques learn entity/relation embeddings from triplets in a KG jointly with third-party data sources, in particular with text (e.g., Wikipedia articles) [47], [48], [49], [50].”
BackgroundEnhancing Knowledge Graph Completion By Embedding Correlations
Pal, S., & Urbani, J. (2017) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3132847.3133143 · Cited by 4
“HolE [10] or variants of TransE like TransH [16] and TransR [7]) or by including external evidence in the process – like word embeddings [15], entities or taxonomies [6, 17] or rules [2, 12, 14].”
BackgroundCross-modal Knowledge Transfer: Improving the Word Embedding of Apple by Looking at Oranges
Both, F., Thoma, S., & Rettinger, A. (2017) · International Conference on Knowledge Capture · doi:10.1145/3148011.3148026 · Cited by 4
“Another approach for joint learning of word embeddings and KG embeddings which are represented in the same vector space is investigated in [26].”
BackgroundLearning from Textual Data in Database Systems
Günther, M., Oehme, P., Thiele, M., & Lehner, W. (2020) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3340531.3412056 · Cited by 4
“However, these joined learning approaches [41, 42, 44, 45] can hardly be adapted to the relations of text values in relational database systems.”
BackgroundDao, A., Kertkeidkachorn, N., & Ichise, R. (2021) · Procedia Computer Science · doi:10.1016/j.procs.2021.08.133 · Cited by 4
KRL_Match: knowledge graph objects matching for knowledge representation learning
Suo, X., Guo, B., Shen, Y. H., Dai, S., Wang, W., Chen, Y., & Zhang, Z. (2022) · Knowledge and Information Systems · doi:10.1007/s10115-022-01764-8 · Cited by 6
“We take TransE [21], pTransE [17], AED [18], KG2E [19], TransG [20], and KBGAN [11] as the baselines on FB15K and WN18.”
BackgroundMethodResultInfluentialJKRL: Joint Knowledge Representation Learning of Text Description and Knowledge Graph
Xu, G., Zhang, Q., Yu, D., Lu, S., & Lu, Y. (2023) · Symmetry · doi:10.3390/sym15051056 · Cited by 4
Usefulness of open domain model for identifying missing software requirements concepts
Zhao, Z., Zhang, L., & Lian, X. (2023) · Software Practice and Experience · doi:10.1002/spe.3285 · Cited by 4
“18,62 Generally, both the domain model and requirements are modeled as fact triplets (i.e., knowledge model and requirement model ).”
BackgroundMethodAutomating Class/Instance Representational Choices in Knowledge Bases
Padia, A., Martin, D., & Patel‐Schneider, P. F. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-03667-6_18 · Cited by 4
Potential Probability of Negative Triples in Knowledge Graph Embedding
Luo, S., & Fang, W. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-04182-3_5 · Cited by 4
A Structural Representation Learning for Multi-relational NetworksPreprint
Li, X., Hong, H., Liu, L., & Cheung, W. K. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.06197 · Cited by 4
Rosso, P., Yang, D., & Cudré-Mauroux, P. (2018) · Springer eBooks · doi:10.1007/978-3-319-63962-8_284-1 · Cited by 5
“A representative work by Wang et al (2014a) introduces a model that combines text corpus and KG to align them in the same vector space and creates KG embeddings and text embeddings.”
BackgroundMethodPangloss: Fast Entity Linking in Noisy Text EnvironmentsPreprint
Conover, M., Hayes, M., Blackburn, S., Skomoroch, P., & Shah, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1807.06036 · Cited by 4
“As input to this system, we compute representational embeddings of both knowledge base entries and surface forms side-by-side in the same vector space [7, 40].”
MethodRosso, P., Yang, D., & Cudré-Mauroux, P. (2019) · Springer eBooks · doi:10.1007/978-3-319-77525-8_284 · Cited by 4
Ma, Z. (2021) · 2021 2nd International Conference on Electronics, Communications and Information Technology (CECIT) · doi:10.1109/cecit53797.2021.00079 · Cited by 3
The concept information of graph granule with application to knowledge graph embedding
Niu, J., Chen, D., Ma, Y., & Li, J. (2024) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-024-02267-4 · Cited by 3
“Wang et al. [14] used entity names along with the description text from Wikipedia to benefit embedding learning.”
Relational Path Mining in Structured Knowledge
Bornea, M. A., & Barker, K. (2015) · International Conference on Knowledge Capture · doi:10.1145/2815833.2815840 · Cited by 3
“[8], [9], [10] and [11] learn word embedding models for entities and their relations to capture the correlations among the facts explicitly stated in the knowledge base.”
BackgroundTowards a Vecsigrafo: Portable Semantics in Knowledge-based Text Analytics.
Denaux, R., & Gómez-Pérez, J. M. (2017) · Cited by 3
Zero or few shot knowledge graph completions by text enhancement with multi-grained attention
Du, Z. (2021) · IEEE International Conference on Tools with Artificial Intelligence (ICTAI) · doi:10.1109/ictai52525.2021.00167 · Cited by 3
HRHE: hybrid relations-guided multi-modal knowledge graph completion using hierarchical embeddings
Lu, X., Li, H., Lu, W., Chang, Y., & Xue, F. (2025) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-025-01150-2 · Cited by 3
“In the upper part, TransE (Bordes et al. 2013), TransH (Wang et al. 2014), and HAKE (Zhang et al. 2020) rely on structured KGs.”
Enhanced anomaly detection in log-based systems using GAN-based models
Farjamfard, E., & Shameli‐Sendi, A. (2025) · Cluster Computing · doi:10.1007/s10586-025-05535-2 · Cited by 3
“The TransE model [ 65] is one of the most effective methods for representing triplets.”
Knowledge Base Completion by Inference from Both Relational and Literal Facts
Wang, Z., & Huang, Y. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-16142-2_39 · Cited by 4
Self-citation
Metadata
- Authors
- Wang, Z., Zhang, J., Feng, J., & Chen, Z.
- Affiliations
- Sun Yat-sen University (CN)
- Venue
- Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)
- Published
- 2014
- Pages
- 1591-1601
- OpenAlex
- W2158028897
- Cited by
- 406
- References
- 22
- Citations by year
- 2026: 4 · 2025: 10 · 2024: 20 · 2023: 22 · 2022: 25 · 2021: 46 · 2020: 66 · 2019: 53 · 2018: 62 · 2017: 45 · 2016: 38 · 2015: 14
- FWCI
- 18.87
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference on Empirical Methods in Natural Language Processing (EMNLP) (publishedVersion, cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Advanced Graph Neural Networks
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Keywords
- knowledge graph embedding, knowledge graph completion, word embeddings, analogical reasoning, Freebase, Word2Vec comparison
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.