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 101–200 of 406
Knowledge Graphs and Big Data Processing
Janev, V., Graux, D., Jabeen, H., & Sallinger, E. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-53199-7 · Cited by 49
“TransH [462] is en extension of TransE, which addresses the limitations of TransE in modeling N-M relations.”
BackgroundAutomatic Synonym Discovery with Knowledge Bases
Qu, M., Ren, X., & Han, J. (2017) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3097983.3098185 · Cited by 39
“[18, 23] exploit entity types to enhance the learned embedding and [7, 28, 31, 34] exploit existing relation facts in knowledge bases as constraints to improve the performances.”
BackgroundBERT-Based Chinese Relation Extraction for Public Security
Hou, J., Li, X., Yao, H., Sun, H., Mai, T., & Zhu, R. (2020) · IEEE Access · doi:10.1109/access.2020.3002863 · Cited by 39
“Because of the large scale of knowledge and the high costs of manual tagging, the technology of relationship extraction technology becomes particularly important since it can add more abundant world knowledge to the KGs and automatically obtain world knowledge [8].”
BackgroundCross-lingual Entity Alignment with Incidental Supervision
Chen, M., Shi, W., Zhou, B., & Roth, D. (2021) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2021.eacl-main.53 · Cited by 45
Multi-level Representations for Fine-Grained Typing of Knowledge Base Entities
Yaghoobzadeh, Y., & Schütze, H. (2017) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/e17-1055 · Cited by 46
Patient Similarity via Joint Embeddings of Medical Knowledge Graph and Medical Entity Descriptions
Lin, Z., Yang, D., & Yin, X. (2020) · IEEE Access · doi:10.1109/access.2020.3019577 · Cited by 41
“To encode the rich semantic representations of words in given medical entity descriptions, we adopt the text model proposed in [39] as our medical entity description embedding model.”
MethodJoint Semantic Synthesis and Morphological Analysis of the Derived Word
Cotterell, R., & Schütze, H. (2018) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00003 · Cited by 49
Knowledge verification for long-tail verticals
Li, F., Dong, X. L., Langen, A., & Yang, L. (2017) · Proceedings of the VLDB Endowment · doi:10.14778/3137628.3137646 · Cited by 37
“Another possibility is to jointly embed web documents and the existing knowledge-base triples into the same vector space [28, 39].”
BackgroundOn2Vec : Embedding-based Relation Prediction for Ontology Population
Chen, M., Tian, Y., Chen, X., Xue, Z., & Zaniolo, C. (2018) · Society for Industrial and Applied Mathematics eBooks · doi:10.1137/1.9781611975321.36 · Cited by 39
“For example, variants of TransE are trained in joint with word embeddings to enable synthesized word embeddings with relational inferences [37, 43], and are combined with alignment models to help cross-lingual knowledge alignment [8, 10].”
MethodTowards holistic Entity Linking: Survey and directions
Oliveira, I. L., Fileto, R., Speck, R., Garcia, L. P. F., Moussallem, D., & Lehmann, J. (2020) · Information Systems · doi:10.1016/j.is.2020.101624 · Cited by 48
“…Fang et al. (2016) [52], the authors combine the entity model with the word model by using two alignment techniques proposed by Wang et al. (2014) [63] (based on Wikipedia anchors and entity names, respectively) and one alignment technique from Zhong et al. (2015) [64] (based on entity…”
MethodCAVA: A Visual Analytics System for Exploratory Columnar Data Augmentation Using Knowledge Graphs
Cashman, D., Xu, S., Das, S., Heimerl, F., Liu, C., Humayoun, S. R., Gleicher, M. L., Endert, A., & Chang, R. (2020) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2020.3030443 · Cited by 42
“, for embedding entities and words into a continuous vector space [72], for extracting relation facts form text [35, 65], for the generation of questions and answers pairs automatically [64], and for parsing and interpretation of user natural language semantically [27].”
EVE: explainable vector based embedding technique using Wikipedia
Qureshi, M. A., & Greene, D. (2018) · Journal of Intelligent Information Systems · doi:10.1007/s10844-018-0511-x · Cited by 45
“Additionally, some works within this category attempt to jointly learn words and entities together with relational facts into the same continuous vector space with the goal of completing facts in a knowledge base (Wang et al. 2014; Wu et al. 2015).”
BackgroundDeep Learning-Based Knowledge Graph Generation for COVID-19
Kim, T., Yun, Y. I., & Kim, N. (2021) · Sustainability · doi:10.3390/su13042276 · Cited by 43
“Embedding an existing knowledge graph using BERT has also been applied to various text classification tasks and used to increase document classification accuracy [54,55].”
MethodMultitask feature learning approach for knowledge graph enhanced recommendations with RippleNet
Wang, Y., Dong, L., Li, Y., & Zhang, H. (2021) · PLoS ONE · doi:10.1371/journal.pone.0251162 · Cited by 37
“The first step is to embed all entities and relationships with knowledge graph embedding (KGE) technology, such as TransE [22], TransR [23], TransH [24], and other Trans series algorithms.”
BackgroundMultimodal learning on graphs for disease relation extraction
Lin, Y., Lu, K., Yu, S., Cai, T., & Žitnik, M. (2023) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2023.104415 · Cited by 45
Corpus-Level Fine-Grained Entity Typing
Yaghoobzadeh, Y., Adel, H., & Schuetze, H. (2018) · Journal of Artificial Intelligence Research · doi:10.1613/jair.5601 · Cited by 37
Propositionalization and embeddings: two sides of the same coin
Lavrač, N., Škrlj, B., & Robnik-Šikonja, M. (2020) · Machine Learning · doi:10.1007/s10994-020-05890-8 · Cited by 37
“ning-suitable format. As knowledge graphs are not necessarily the only source of available information, algorithms exploit also other information, e.g., textual information available for each triplet [92]. Recent trends in knowledge graph embeddings also explore how symbolic, logical structures could be used during em…”
BackgroundALGAN: Time Series Anomaly Detection with Adjusted-LSTM GAN
Bashar, M. A., & Nayak, R. (2025) · International Journal of Data Science and Analytics · doi:10.1007/s41060-025-00810-2 · Cited by 40
XLM-K: Improving Cross-Lingual Language Model Pre-training with Multilingual Knowledge
Jiang, X., Liang, Y., Chen, W., & Duan, N. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i10.21330 · Cited by 48
Knowledge Graph Completion by Context-Aware Convolutional Learning with Multi-Hop Neighborhoods
Oh, B., Seo, S., & Lee, K.-H. (2018) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3269206.3271769 · Cited by 37
“[56] jointly embeds knowledge graphs and text (Wikipedia anchors and entity names) into the same vector space.”
BackgroundUsing dynamic knowledge graphs to detect emerging communities of knowledge
Aparício, J. T., Arsénio, E., Santos, F. C., & Henriques, R. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.111671 · Cited by 39
Jointly Embedding Entities and Text with Distant Supervision
Newman-Griffis, D. R., Lai, A. M., & Fosler‐Lussier, E. (2018) · Workshop on Representation Learning for NLP (RepL4NLP) · doi:10.18653/v1/w18-3026 · Cited by 38
“Wang et al. (2014), Yamada et al. (2016), and Cao et al. (2017) all use a joint embedding method, learning representations of text from a large corpus and entities from a knowledge graph; however, they rely on the disambiguated entity annotations in Wikipedia to align their models.”
MethodFeature-Attention Graph Convolutional Networks for Noise Resilient Learning
Shi, M., Tang, Y., Zhu, X., Zhuang, Y., Lin, M., & Liu, J. (2022) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2022.3143798 · Cited by 34
Beyond word embeddings: learning entity and concept representations from large scale knowledge bases
Shalaby, W., Zadrozny, W., & Jin, H. (2018) · Information Retrieval · doi:10.1007/s10791-018-9340-3 · Cited by 31
“Second, methods that jointly learn embeddings of words and concepts in the same semantic space (Wang et al. 2014; Fang et al. 2016; Yamada et al. 2016; Camacho-Collados et al. 2016; Fang et al. 2016; Cao et al. 2017; Shalaby and Zadrozny 2017; Phan et al. 2017).”
MethodTriple Classification Using Regions and Fine-Grained Entity Typing
Dong, T., Wang, Z., Li, J., Bauckhage, C., & Cremers, A. B. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.330177 · Cited by 36
“…Kasneci, and Weikum 2007; Bollacker et al. 2008) are very useful for AI applications, e.g. question-answering, query expansion, information retrieval, document classification (Manning, Ragha-van, and Sch¨utze 2008; Socher et al. 2013; Bordes et al. 2013; Wang et al. 2014a; Wang and Li 2016).”
BackgroundInfluentialSelf-citationUtilizing Knowledge Graphs for Neural Machine Translation Augmentation
Moussallem, D., Ngomo, A.-C. N., Buitelaar, P., & Arčan, M. (2019) · International Conference on Knowledge Capture · doi:10.1145/3360901.3364423 · Cited by 29
“Wang et al. [47] proposed a technique of learning to embed structured and unstructured data (such as text) jointly in an effort to augment the prediction models.”
MethodUtilizing Textual Information in Knowledge Graph Embedding: A Survey of Methods and Applications
Lu, F., Cong, P., & Huang, X. (2020) · IEEE Access · doi:10.1109/access.2020.2995074 · Cited by 38
“In Literature [26], when word w and context word v are considered a positive fact ( w , v ) with implict relation.”
BackgroundMethodInfluentialKnowledge Graph-Based Clinical Decision Support System Reasoning: A Survey
Xiang, X., Wang, Z., Jia, Y., & Fang, B. (2019) · IEEE International Conference on Data Science in Cyberspace · doi:10.1109/dsc.2019.00063 · Cited by 34
“This ambiguity disqualifies the doctors’ right to understand how and why a certain machine-created diagnosis is made, not to mention enforcing them to trust the result it offered [68].”
BackgroundSelf-citationMEmbER: Max-Margin Based Embeddings for Entity Retrieval
Jameel, S., Bouraoui, Z., & Schockaert, S. (2017) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3077136.3080803 · Cited by 27
“For example, in [42] and [49] a model is proposed which combines a component that is similar in spirit to Skip-gram, to exploit textual descriptions of entities, with a component that is similar in spirit to TransE, to exploit the triples that are available.”
MethodEnriching Translation-Based Knowledge Graph Embeddings Through Continual Learning
Song, H.-J., & Park, S.-B. (2018) · IEEE Access · doi:10.1109/access.2018.2874656 · Cited by 31
“Most of them utilize external resources such as entity names and descriptions to predict embeddings of newly appearing entities or relations [22]–[25].”
BackgroundNeural Machine Translation for Query Construction and CompositionPreprint
Soru, T., Marx, E., Valdestilhas, A., Esteves, D., Moussallem, D., & Publio, G. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.10478 · Cited by 27
“Knowledge graph jointly embedded with S PARQL operators (Wang et al., 2014) can be utilized in the target space.”
MethodRepresentation Learning of Knowledge Graphs with Entity Attributes and Multimedia Descriptions
Zuo, Y., Fang, Q., Qian, S., Zhang, X., & Xu, C. (2018) · IEEE International Conference on Multimedia Big Data · doi:10.1109/bigmm.2018.8499179 · Cited by 30
“[11] projects its associated entity and text information into a common vector space with alignment model.”
BackgroundHET-KG: Communication-Efficient Knowledge Graph Embedding Training via Hotness-Aware Cache
Dong, S., Miao, X., Liu, P., Wang, X., Cui, B., & Li, J. (2022) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde53745.2022.00177 · Cited by 29
Neural embedding-based indices for semantic search
Lashkari, F., Bagheri, E., & Ghorbani, A. A. (2019) · Information Processing & Management · doi:10.1016/j.ipm.2018.10.015 · Cited by 28
“Wang, Zhang, Feng, and Chen (2014) and Yamada, Shindo, Takeda, and Takefuji (2016b) considered embedding words and entities into the same continuous vector space for the sake of named entity disambiguation.”
BackgroundAugmenting Neural Machine Translation with Knowledge GraphsPreprint
Moussallem, D., Arčan, M., Ngomo, A.-C. N., & Buitelaar, P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.08816 · Cited by 27
“(2) Wang et al. (2014) proposed a technique of learning to embed structured and unstructured data (such as text) jointly in an effort to augment the prediction models.”
BackgroundJoint semantics and data-driven path representation for knowledge graph reasoning
Niu, G., Li, B. H., Zhang, Y., Sheng, Y., Shi, C., Li, J., & Pu, S. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.02.011 · Cited by 25
Schema-Aware Hyper-Relational Knowledge Graph Embeddings for Link Prediction
Lu, Y., Yang, D., Wang, P., Rosso, P., & Cudré-Mauroux, P. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2023.3323499 · Cited by 32
Logic Rules Powered Knowledge Graph EmbeddingPreprint
Wang, P., Dou, D., Wu, F., de Silva, N., & Jin, L. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.03772 · Cited by 29
“Several recent works try to incorporate other available knowledge, e.g., relation paths [12, 14], entity types [7], Wikipedia anchors [26], and entity descriptions [32].”
BackgroundImproving Word Embeddings with Convolutional Feature Learning and Subword Information
Cao, S., & Lu, W. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.10993 · Cited by 24
“Other than improving the techniques to model the contextual information, previous works have also leveraged existing lexical resources to improve word embeddings, such as RCM (Yu and Dredze 2014), knowledge embedding (Wang et al. 2014) and SensEmbed (Iacobacci, Pilehvar, and Nav-igli 2015).”
MethodIntegrating Image-Based and Knowledge-Based Representation Learning
Xie, R., Heinrich, S., Liu, Z., Weber, C., Yao, Y., Wermter, S., & Sun, M. (2019) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2019.2906685 · Cited by 28
“To utilize rich textual information, Wang et al. [25] project both entities and words into a joint vector space with alignment models.”
MethodEnabling Remote School Education using Knowledge Graphs and Deep Learning Techniques
Nair, L. S., Shivani, M. K., & Cheriyan, J. (2022) · Procedia Computer Science · doi:10.1016/j.procs.2022.12.064 · Cited by 25
Incorporating Extra Knowledge to Enhance Word Embedding
Roy, A., & Pan, S. (2020) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2020/686 · Cited by 24
“Among the papers we surveyed, [Xu et al. , 2014; Bian et al. , 2014; Wang et al. , 2014; Cao et al. , 2017] reported model performance using this task.”
BackgroundMethodImprove the translational distance models for knowledge graph embedding
Zhang, S., Sun, Z., & Zhang, W. (2020) · Journal of Intelligent Information Systems · doi:10.1007/s10844-019-00592-7 · Cited by 26
“Some previous work, like (Wang et al. 2014), introduced textural resources to address this ’out-of-kb’ problem.”
BackgroundMethodInfluentialFusing external knowledge resources for natural language understanding techniques: A survey
Wang, Y., Wang, W., Chen, Q., Huang, K., Nguyen, A., De, S., & Hussain, A. (2022) · Information Fusion · doi:10.1016/j.inffus.2022.11.025 · Cited by 32
Non-translational Alignment for Multi-relational Networks
Li, S., Li, X., Ye, R., Wang, M., Su, H., & Ou, Y. (2018) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/581 · Cited by 23
“…nodes may be of different relation types, most so-Proceedings lutions apply the trans-family, such as TransE [Bordes et al. , 2013] , TransH [Wang et al. , 2014b] and pTransE [Lin et al. , 2015a], to generate vector representations for nodes and relations in multi-relational network…”
BackgroundConvolutional Network Embedding of Text-Enhanced Representation for Knowledge Graph Completion
Zhao, F., Xu, T., Jin, L., & Jin, H. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3039750 · Cited by 22
Conceptualized and Contextualized Gaussian Embedding
Chen, Q., Feng, F., Wen, L., & Chua, T. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i15.17613 · Cited by 22
“2017) or external knowledge (Wang et al. 2014; Yu and Dredze 2014; Liu et al. 2015, 2018; Niu et al. 2017; Alsuhaibani et al. 2018; Zhang et al. 2019) into point embedding shows significant improvements.”
BackgroundUnsupervised Learning of Distributional Relation Vectors
Bouraoui, Z., Jameel, S., & Schockaert, S. (2018) · ORCA Online Research @Cardiff (Cardiff University) · doi:10.18653/v1/p18-1003 · Cited by 21
“In contrast, we will directly learn relation vectors from corpus statistics, which will have the important advantage that we can focus on words that describe the interaction between the two words s and t, i.e. words that commonly occur in sentences that contain both s and t, but are comparatively rare in sentences tha…”
BackgroundResultInfluentialEntity Embeddings with Conceptual Subspaces as a Basis for Plausible Reasoning
Shoaib, J., & Schockaert, S. (2016) · Frontiers in artificial intelligence and applications · doi:10.3233/978-1-61499-672-9-1353 · Cited by 27
HARP: A Novel Hierarchical Attention Model for Relation Prediction
Wang, Y., & Zhang, H. (2021) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3424673 · Cited by 21
“[77] combines entity embeddings with word embeddings into a joint continuous vector space by alignment models using entity names or Wikipedia anchors.”
MethodRETA: A Schema-Aware, End-to-End Solution for Instance Completion in Knowledge Graphs
Rosso, P., Yang, D., Ostapuk, N., & Cudré-Mauroux, P. (2021) · International World Wide Web Conference (WWW) · doi:10.1145/3442381.3449883 · Cited by 29
“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) [36, 41, 44, 49].”
BackgroundKnowledge Graph Embedding with Entity Neighbors and Deep Memory NetworkPreprint
Wang, K., Liu, Y., Xu, X., & Lin, D. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.03752 · Cited by 24
“To solve flaws in dealing with ‘1-to-N’, ‘N-to-1’, and ‘N-to-N’ relations (Lin et al. 2015b), some variants of TransE such as TransH (Wang et al. 2014b), TransR (Lin et al. 2015b) and TransD (Ji et al. 2015) are proposed.”
BackgroundUrsuleanu, T. F., Luca, A. R., Gheorghe, L., Grigorovici, R., Iancu, S., Hlusneac, M., Preda, C., & Grigorovici, A. (2021) · Diagnostics · doi:10.3390/diagnostics11081373 · Cited by 26
A Retrieve-and-Read Framework for Knowledge Graph Link Prediction
Pahuja, V., Wang, B., Latapie, H. M., Srinivasa, J., & Su, Y. (2023) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3583780.3614769 · Cited by 23
“It finds applications in relation extraction (Wang et al., 2014; Chen and Badlani, 2020), question answering (Huang et al.”
BackgroundJoint Word and Entity Embeddings for Entity Retrieval from a Knowledge Graph
Nikolaev, F., & Kotov, A. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-45439-5_10 · Cited by 26
“Several studies [37, 39, 46] proposed a hybrid between entity and word embeddings by employing a loss function, which includes both a TransE-based component to model relations between entities and a word2vec-based component to model semantic relations between the words along with the third component, whose purpose is…”
BackgroundProceedings of The Third Workshop on Representation Learning for NLP
(2018) · doi:10.18653/v1/w18-30 · Cited by 20
Amador-Domínguez, E., Serrano, E., & Manrique, D. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.12.010 · Cited by 21
AutoExtend: Combining Word Embeddings with Semantic Resources
Rothe, S., & Schütze, H. (2017) · Computational Linguistics · doi:10.1162/coli_a_00294 · Cited by 19
“Wang et al. (2014) used Freebase to learn embeddings for entities and words.”
MethodConstruction of traditional Chinese medicine Knowledge Graph using Data Mining and Expert Knowledge
Cheng, B., Zhang, Y., Cai, D., Qiu, W., & Shi, D. (2018) · IEEE International Conference on Network Infrastructure and Digital Content (IC-NIDC) · doi:10.1109/icnidc.2018.8525665 · Cited by 19
Unsupervised Embedding Enhancements of Knowledge Graphs using Textual Associations
Veira, N., Keng, B., Padmanabhan, K., & Veneris, A. G. (2019) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/725 · Cited by 19
Drug repurposing through joint learning on knowledge graphs and literaturePreprint
Alshahrani, M., & Hoehndorf, R. (2018) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/385617 · Cited by 19
Knowledge Graph Embedding with Triple Context
Shi, J., Gao, H., Qi, G., & Zhou, Z. (2017) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3132847.3133119 · Cited by 18
“…can be considered as the compatibility between h and its neighbor context, it is formalized as a softmax-like representation, which is also used in [12] and has been validated, as follows: where f 1 „(cid:1) ; (cid:1)” is the function that describes the correlation between an arbitrary entity h ′…”
MethodRelevance-based entity selection for ad hoc retrieval
Ensan, F., & Al-Obeidat, F. N. (2019) · Information Processing & Management · doi:10.1016/j.ipm.2019.05.005 · Cited by 21
A Model of Text-Enhanced Knowledge Graph Representation Learning With Mutual Attention
Wang, Y., Zhang, H., Shi, G., Liu, Z., & Zhou, Q. (2020) · IEEE Access · doi:10.1109/access.2020.2981212 · Cited by 22
“However, attention values assigned for the knowledge graph representation learning (i.e., structure representation) and for the textual relation representation learning (i.e., text representation) haven’t been fully integrated [19], [22], [30]–[32].”
BackgroundText-Graph Enhanced Knowledge Graph Representation Learning
Hu, L., Zhang, M., Li, S., Shi, J., Shi, C., Yang, C. H., & Liu, Z. (2021) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2021.697856 · Cited by 21
“Wang et al. (2014a) utilized entity names and Wikipedia anchors to align the embeddings of entities and words in the same space.”
MethodGaussian Word Embedding with a Wasserstein Distance LossPreprint
Sun, C. C., Yan, H. R., Qiu, X., & Huang, X. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.07016 · Cited by 20
“Wang et al. (2014) use knowledge mapping information and (Tissier, Gravier, and Habrard 2017) introduce dictionary information to train the word vectors in order to achieve significant results.”
MethodYang, J., Yang, L. T., Gao, Y., Liu, H., & Xie, X. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2021.3100978 · Cited by 17
“Among them, triplets classification has been widely used to evaluate the effect of many existing inference models [32].”
BackgroundActive Learning for Black-Box Semantic Role Labeling with Neural Factors
Wang, C., Chiticariu, L., & Li, Y. (2017) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2017/405 · Cited by 21
“Inspired by TransE [Bordes et al. , 2013; Wang et al. , 2014], we first de-fine the score of closeness between predicate and one of its arguments as: where ~p and ~a are the vector representation of predicate span p and argument span a respectively, b is a constant for bias designated for adjusting…”
MethodAnalyzing Knowledge Graph Embedding Methods from a Multi-Embedding Interaction PerspectivePreprint
Tran, H. N., & Takasu, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.11406 · Cited by 20
“Here, we only review the works that are directly related to this paper, namely models that use only triples, not external data such as text [32] or graph structure such as relation paths [18].”
Research hypothesis generation over scientific knowledge graphs
Borrego, A., Dessì, D., Ayala, D., Hernández, I., Osborne, F., Recupero, D. R., Buscaldi, D., Ruiz, D., & Motta, E. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113280 · Cited by 29
On the Generative Discovery of Structured Medical Knowledge
Zhang, C., Li, Y., Du, N., Fan, W., & Yu, P. S. (2018) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3219819.3220010 · Cited by 16
“Knowledge Graph Completion : Existing knowledge graph completion methods [6, 13, 22, 38, 43, 44] are discriminative models.”
A semi-supervised model for knowledge graph embedding
Zhu, J., Zheng, Z., Yang, M., Fung, G. P. C., & Tang, Y. Z. (2019) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-019-00653-z · Cited by 16
“Wang et al. (2014) showed promising improvements to the accuracy of predicting facts by jointly embed knowledge and text into the same space.”
BackgroundPhrase embedding learning from internal and external information based on autoencoder
Li, R., Yu, Q., Huang, S., Shen, L., Wei, C., & Sun, X. (2020) · Information Processing & Management · doi:10.1016/j.ipm.2020.102422 · Cited by 18
I Know What You Want to Express: Sentence Element Inference by Incorporating External Knowledge Base
Wei, X., Huang, H., Nie, L., Zhang, H., Mao, X.-L., & Chua, T. (2016) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2016.2622705 · Cited by 17
“The simple form and its expansibility makes the model widely utilized in many joint learning models to incorporate knowledge information into existing models [29], [44].”
BackgroundInterpretable and Compositional Relation Learning by Joint Training with an Autoencoder
Takahashi, R., Tian, R., & Inui, K. (2018) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p18-1200 · Cited by 17
“…et al., 2013; Hixon et al., 2015; Nickel et al., 2016a) and KBC has inspired a huge amount of research (Bordes et al., 2013; Riedel et al., 2013; Socher et al., 2013; Wang et al., 2014b,a; Xiao et al., 2016; Nguyen et al., 2016; Toutanova et al., 2016; Das et al., 2017; Hayashi and Shimbo, 2017).”
BackgroundInstances and concepts in distributional space
Boleda, G., Gupta, A., & Padó, S. (2017) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/e17-2013 · Cited by 18
“…representations of instances for NLP tasks: For instance, Lewis and Steedman (2013) use the distributional similarity of named entities to build a type system for a semantic parser, and several works in Knowledge Base completion use entity embeddings (see Wang et al. (2014) and references there).”
MethodSelf-Learning and Embedding Based Entity Alignment
Guan, S., Jin, X., Jia, Y., Wang, Y., Shen, H., & Cheng, X. (2017) · IEEE International Conference on Big Knowledge (ICBK) · doi:10.1109/icbk.2017.15 · Cited by 15
Incorporating logic rules with textual representations for interpretable knowledge graph reasoning
Pan, Y., Liu, J., Zhang, L., & Huang, Y. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110787 · Cited by 18
Knowledge Graph Embeddings: Open Challenges and Opportunities
Biswas, R., Kaffee, L.-A., Cochez, M., Dumbrava, S., Jendal, T. E., Lissandrini, M., López, V., Mencía, E. L., Paulheim, H., Sack, H., et al. (2023) · Transactions on Graph Data and Knowledge · doi:10.4230/tgdk.1.1.4 · Cited by 41
Multi-Task Learning for Entity Recommendation and Document Ranking in Web Search
Huang, J., Wang, H., Zhang, W., & Liu, T. (2020) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3396501 · Cited by 15
“To alleviate this problem, several approaches have been proposed in previous studies, e.g., using word embeddings of the entity names to represent novel entities [44, 53], or building representations for novel entities from their descriptions [49, 52].”
MethodKnowledge Representation via Joint Learning of Sequential Text and Knowledge GraphsPreprint
Wu, J., Xie, R., Liu, Z., & Sun, M. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1609.07075 · Cited by 18
“To address the first problem, TransH (Wang et al., 2014b) models translating operations between entities on relation-specific hyperplanes.”
BackgroundMethodInfluentialZero-shot text classification with knowledge resources under label-fully-unseen setting
Wang, Y., Wang, W., Chen, Q., Huang, K., Nguyen, A., & De, S. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128580 · Cited by 16
Triple Context-Based Knowledge Graph Embedding
Gao, H., Shi, J., Qi, G., & Wang, M. (2018) · IEEE Access · doi:10.1109/access.2018.2875066 · Cited by 14
“The approximated probability P (h|Cn(h); Θ) can be considered as the compatibility between h and its neighbor context, it is formalized as a softmax-like representation, which is also used in [1] and has been validated as follows:”
BackgroundZhang, M., Geng, G.-H., Zeng, S., & Jia, H.-P. (2020) · Entropy · doi:10.3390/e22101168 · Cited by 11
“[30] used the TransE model to learn the knowledge representation in a knowledge graph incorporating textual data, and then, they used the link information in Wikipedia to make the word representation of the entities in the text as close as possible to the entities in the knowledge graph.”
MethodUnderstanding Negative Sampling in Knowledge Graph Embedding
Qian, J., Li, G., Atkinson, K. M., & Yue, Y. (2021) · International Journal of Artificial Intelligence & Applications · doi:10.5121/ijaia.2021.12105 · Cited by 20
“Besides, Wang et al. [39] considers text information and puts forward a joint model to accomplish the embedding process.”
Multi-source Knowledge Embedding Research of Knowledge Graph
Ren, L., Lu, J., & Wei, G. (2019) · doi:10.1109/iccsd.2019.8842938 · Cited by 14
“[17] used the information in the text to expand the scope of knowledge representation learning, and to complement the knowledge that was not in the knowledge graph.”
MethodWorld Knowledge as Indirect Supervision for Document Clustering
Wang, C., Song, Y., Roth, D., Zhang, M., & Han, J. (2016) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/2953881 · Cited by 13
Wei, X., Zhang, Y., & Wang, H. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07923-w · Cited by 14
“[5] presented a text mode and a knowledge model to learn the word representation in Wikipedia and the knowledge representation in Freebase respectively and employed Wikipedia anchors or entity names to align knowledge and text.”
MethodLearning Better Word Embedding by Asymmetric Low-Rank Projection of Knowledge Graph
Tian, F., Gao, B., Chen, E., & Liu, T. (2016) · Journal of Computer Science and Technology · doi:10.1007/s11390-016-1651-5 · Cited by 13
“RNet : the joint embedding model in [23] and [21], which adopts the objective min || h + r − t || 22 in the knowledge model.”
BackgroundMethodResultInfluentialInfusing Collaborative Recommenders with Distributed Representations
Zanotti, G., Horvath, M., Barbosa, L. N., Immedisetty, V. T. K. G., & Gemmell, J. F. (2016) · Workshop on Deep Learning for Recommender Systems (DLRS) · doi:10.1145/2988450.2988455 · Cited by 14
“These techniques have been extended to social networks [24], knowledge graphs [35], sentiment analysis [36] and opinion mining [12].”
BackgroundHEER: Heterogeneous graph embedding for emerging relation detection from news
Zhang, J., Lu, C.-T., Zhou, M., Xie, S., Chang, Y., & Yu, P. S. (2016) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2016.7840673 · Cited by 15
Self-citationJana, A., & Goyal, P. (2018) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n18-1043 · Cited by 13
Phrase embedding learning based on external and internal context with compositionality constraint
Li, M., Lu, Q., Xiong, D., & Long, Y. (2018) · Knowledge-Based Systems · doi:10.1016/j.knosys.2018.04.009 · Cited by 13
Deep Learning in Knowledge Graph
Liu, Z., & Han, X. (2018) · Springer eBooks · doi:10.1007/978-981-10-5209-5_5 · Cited by 15
“For textural information, Wang et al. (2014a) and Zhong et al. (2015) propose to jointly embed both entities and words into a unified semantic space by aligning them with entity names, descriptions, and Wikipedia anchors.”
BackgroundJurek, A., & Deepak, P. (2018) · Unsupervised and semi-supervised learning · doi:10.1007/978-3-030-01872-6_3 · Cited by 13
Alshahrani, M., Almansour, A., Alkhaldi, A., Thafar, M. A., Uludağ, M., Essack, M., & Hoehndorf, R. (2022) · PeerJ · doi:10.7717/peerj.13061 · Cited by 15
“…methods, in particular translational embeddings ( Bordes et al., 2013 ; Nickel, Rosasco & Poggio, 2016 ; Dai & Yeung, 2006 ), that have previously been combined successfully with textual information ( Wang et al., 2014c ), and evaluate their performance for prediction of biological relations.”
Representation Learning of Entities and Documents from Knowledge Base DescriptionsPreprint
Yamada, I., Shindo, H., & Takefuji, Y. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.02960 · Cited by 13
“…the model by Hu et al. to learn both the category representations and entity representations using the category information of the KB. Additionally, relational embedding models (Bordes et al., 2013; Wang et al., 2014; Lin et al., 2015) learn the entity representations for link prediction tasks.”
BackgroundMethodMapping Text to Knowledge Graph Entities using Multi-Sense LSTMsPreprint
Kartsaklis, D., Pilehvar, M. T., & Collier, N. (2018) · arXiv (Cornell University) · doi:10.17863/cam.35220 · Cited by 16
Automatic Synonym Discovery with Knowledge BasesPreprint
Qu, M., Ren, X., & Han, J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.08186 · Cited by 13
“[18, 23] exploit entity types to enhance the learned embedding and [7, 28, 31, 34] exploit existing relation facts in knowledge bases as constraints to improve the performances.”
BackgroundEncoding Prior Knowledge with Eigenword Embeddings
Osborne, D., Narayan, S., & Cohen, S. B. (2016) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00108 · Cited by 12
“Wang et al. (2014) propose a method for jointly embedding entities (from FreeBase, a large community-curated knowledge base) and words (from Wikipedia) into the same continuous vector space.”
Method
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.