Text-Enhanced Representation Learning for Knowledge Graph

By Zhigang Wang, Juan-Zi Li. 2016

215 citations recorded by the source corpus.

How researchers see this paper

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

1. Xiang Wang
2. Xiangnan He
3. Tat-seng Chua
4. Mohit Bansal
5. Yixin Cao
6. Liang Yao
7. Chen Gao
8. Zhenguang Liu

Citations in the corpus

• Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences (2019, methodology): “To address these problems, a host of methods extended TransE by introducing additional hyperplanes [42], vector spaces [23], textual information [41] and relational path [22].”
• Billion-scale Commodity Embedding for E-commerce Recommendation in Alibaba (2018, background): “ther embedded a complicate knowledge graph with the node in a hierarchical structure, like sub-categories, etc. Besides, textual information related to the nodes are incorporated into graph embedding [19, 24, 26, 27]. Moreover, in [5], Chang et al. propose a deep learning framework to simultaneously”
• Entity Alignment between Knowledge Graphs Using Attribute Embeddings (2019, methodology): “In recent years, several studies propose improvements over TransE: TransH (Wang et al. 2014), TransR (Lin et al. 2015), and TransD (Ji et al. 2015) use a distributed representation to separate the relationship vector space from the entity vector space; DKRL (Xie et al. 2016) and TEKE (Wang and Li 20”
• 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].”
• PaperRobot: Incremental Draft Generation of Scientific Ideas (2019, methodology): “Similar to (Wang and Li, 2016; Xu et al., 2017), we enrich entity representation by combining the contextual sentences that include the target entity and its neighbors from the graph structure.”
• Knowledge Graph Embedding for Link Prediction (2020, methodology): “We refer the reader to works discussing how to leverage additional sources of information, such as textual captions [58],[65],[3], images [70] or pre-computed rules [20]; see [18] for a survey exclusive to these models.”
• Learning Intents behind Interactions with Knowledge Graph for Recommendation (2021, methodology): “Embedding-based Methods [1, 4, 16, 35, 37, 51] focus mainly on the first-order connectivity (i.e., user-item pairs in interaction data, triplets in KG), hire KG embedding techniques (e.g., TransE [3] and TransH [46]) to learn entity embeddings, and then use them as prior or context information of it”
• KG-BERT: BERT for Knowledge Graph Completion (2019, methodology): “On the other hand, syntactic and semantic information in large-scale text data is not fully utilized, as they only employ entity descriptions, relation mentions or word co-occurrence with entities (Wang and Li 2016; Xu et al. 2017; An et al. 2018).”
• Knowledge Graph Embedding: A Survey of Approaches and Applications (2017, methodology): “, 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-”