Open-World Knowledge Graph Completion

By Baoxu Shi, Tim Weninger. AAAI Conference on Artificial Intelligence, 2017

330 citations recorded by the source corpus.

Knowledge Graphs (KGs) have been applied to many tasks including Web search, link prediction, recommendation, natural language processing, and entity linking. However, most KGs are far from complete and are growing at a rapid pace. To address these problems, Knowledge Graph Completion (KGC) has been proposed to improve KGs by filling in its missing connections. Unlike existing methods which hold a closed-world assumption, i.e., where KGs are fixed and new entities cannot be easily added, in the present work we relax this assumption and propose a new open-world KGC task. As a first attempt to solve this task we introduce an open-world KGC model called ConMask. This model learns embeddings of the entity's name and parts of its text-description to connect unseen entities to the KG. To mitigate the presence of noisy text descriptions, ConMask uses a relationship-dependent content masking to extract relevant snippets and then trains a fully convolutional neural network to fuse the extracted snippets with entities in the KG. Experiments on large data sets, both old and new, show that ConMask performs well in the open-world KGC task and even outperforms existing KGC models on the standard closed-world KGC task.

Subfields: Artificial Intelligence, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/3a5830800f7b471dafee2a1e6e070f45d9b3f7c7

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. Bing Liu
2. Philip S. Yu
3. B. Liu
4. Sahisnu Mazumder
5. Erik Cambria
6. Hu Xu
7. Shuai Wang
8. Shirui Pan

In Molecular Biology

1. Shirui Pan
2. Philip S. Yu
3. B. Liu
4. Yi Chang
5. Jian Tang
6. Nianzu Ma
7. J. Hendler
8. Shuai Wang

Citations in the corpus

• A benchmarking study of embedding-based entity alignment for knowledge graphs (2020, unknown): “Extracting additional information from the open Web to enrich long-tail entities is also a meaningful direction [76].”
• KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation (2019, methodology): “Inductive Embedding Above KE methods learn entity embeddings only from KG and are inherently transductive, while some works (Wang et al., 2014; Xie et al., 2016; Yamada et al., 2016; Cao et al., 2017; Shi and Weninger, 2018; Cao et al., 2018) incorporate textual metadata such as entity names or desc”
• Structure-Augmented Text Representation Learning for Efficient Knowledge Graph Completion (2020, methodology): “When applied to KGC, some approaches [28, 29] directly replace the graph embeddings with their text embedding.”
• Lifelong and Interactive Learning of Factual Knowledge in Dialogues (2019, background): “Shi and Weninger (2018) handles unknown entities by exploiting an external”
• Continuous and Interactive Factual Knowledge Learning in Verification Dialogues (2020, methodology): “Note that although [45, 44] deal with OKBC, they infer facts using a text corpus, while we do through user interactions.”
• A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multi-Modal (2022, background): “Facts # Test Facts ATOMIC [205] 304,388 9 610,536 87,700 87,701 Countries [206] 271 2 1,110 24 24 CoDEX-S [207] 2,034 42 32,888 3,654 3656 CoDEX-M [207] 17,050 51 185,584 20620 20622 CoDEX-L [207] 77,951 69 551,193 30,622 30622 ConceptNet [208] 28,370,083 50 27,259,933 3,407,492 3,407,492 ConceptNet”
• Knowledge Graph Completion: A Review (2020, background): “According to different task scenarios, knowledge graph completion can be divided into closed environment knowledge graph completion and open environment knowledge graph completion [19].”
• A Survey on Knowledge Graphs: Representation, Acquisition, and Applications (2020, background): “ConMask [67] proposes relationship-dependent content masking over the entity description to select relevant snippets of given relations, and CNN-based target fusion to complete the knowledge graph with unseen entities.”
• Deep learning for noise-tolerant RDFS reasoning (2019, background): “Data-driven KGC models “heavily rely on the connectivity of the existing KG and are best able to predict relationships between existing, well-connected entities” [4, 1].”
• Knowledge Graphs: Opportunities and Challenges (2023, methodology): “For instance, the ConMask model (Shi and Weninger 2018) has been proposed to predict the unseen entities in knowledge graphs.”
• HyTE: Hyperplane-based Temporally aware Knowledge Graph Embedding (2018, background): “corporate type consistency information to further improve our model and also integrate HyTE with open-world knowledge graph completion (Shi and Weninger, 2018).”
• Towards a Continuous Knowledge Learning Engine for Chatbots (2018, methodology): “Recently, (Shi and Weninger, 2017) proposed a method using external text corpus to perform inference on unknown entities.”