Aligning Knowledge and Text Embeddings by Entity Descriptions

By Hua Zhong, Jianwen Zhang, Zhen Wang, Haifang Wan, Zheng Chen. 2015

165 citations recorded by the source corpus.

We study the problem of jointly embedding a knowledge base and a text corpus. The key issue is the alignment model making sure the vectors of entities, relations and words are in the same space. Wang et al. (2014a) rely on Wikipedia anchors, making the applicable scope quite limited. In this paper we propose a new alignment model based on text descriptions of entities, without dependency on anchors. We require the embedding vector of an entity not only to fit the structured constraints in KBs but also to be equal to the embedding vector computed from the text description. Extensive experiments show that, the proposed approach consistently performs comparably or even better than the method of Wang et al. (2014a), which is encouraging as we do not use any anchor information.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xing Xie
2. Minlie Huang
3. Xiaoyan Zhu
4. Maosong Sun
5. Zhiyuan Liu
6. Wenjie Li
7. Hongwei Wang
8. Miao Zhao

Citations in the corpus

• RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems (2018, methodology): “is hence defined as fr(h,t)= h⊤diag(r)t = ˝ d i=1 [r]i ·[h]i ·[t]i. Researchers also propose incorporating auxiliary information, such as entity types [39], logic rules [21], and textual descriptions [46] to assist KGE. However, these methods are more suitable for in-graph applications such as link ”
• Pre-trained models for natural language processing: A survey (2020, background): “Early studies [197, 217, 201, 205] focused on learning knowledge graph embeddings and word embedding jointly.”
• Text-Enhanced Representation Learning for Knowledge Graph (2016, background): “[Zhong et al., 2015] extends the joint model of [Wang et al., 2014a] and aligns knowledge and text embeddings by entity descriptions.”
• Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendation (2019, methodology): “ations, such as RESCAL [20], ANALOGY [19], and HolE [14]. Recently, researchers also propose incorporating auxiliary information, such as entity types [36], logic rules [24], and textual descriptions [46] to assist KGE. The above KGE methods can also be incorporated into MKR as the implementation of”
• SSE: Semantically Smooth Embedding for Knowledge Graphs (2017, background): “This section briefly reviews two lines of related work: KG embedding and manifold learning.”
• SSP: Semantic Space Projection for Knowledge Graph Embedding with Text Descriptions (2016, methodology): “Notice that the “Jointly” model involves much more additional data to produce the result, but SSP also has an remarkable advantage against it.”
• Knowledge Transfer for Out-of-Knowledge-Base Entities : A Graph Neural Network Approach (2017, background): “There have been some attempts to obtain the embeddings for OOKB entities using external resources [Wang et al. , 2014a; Fang et al. , 2016; Zhong et al. , 2015].”
• Augmenting Neural Machine Translation with Knowledge Graphs (2019, background): “Additionally, Zhong et al. (2015) introduced an alignment of entities and word embeddings considering the description of entities.”
• Representation Learning of Knowledge Graphs with Hierarchical Types (2016, methodology): “[Wang et al., 2014a; Zhong et al., 2015] encode both entities and words into a joint continuous vector space by alignment models using Wikipedia anchors, entity names or entity descriptions.”
• Representation Learning of Knowledge Graphs with Entity Descriptions (2016, background): “(Zhong et al. 2015) extends the joint model and aligns knowledge and text embeddings by entity descriptions.”
• Knowledge Graph Embedding: A Survey of Approaches and Applications (2017, background): “, entity types [25], [26], relation paths [27], [28], [29], textual descriptions [30], [31], [32], [33], and even logical rules [23], [34], [35], to learn more pre-”
• Knowledge Graph Embedding Based Question Answering (2019, methodology): “Attempts [37, 38, 50] have also been made to apply TransE and word2vec [28] to model a KG and a corpus respectively, and then fuse them based on anchors in Wikipedia [38], entity descriptions [50], or contextual words of predicates/entities learned from the corpus [37].”