We present a baseline approach for cross-modal knowledge fusion. Different basic fusion methods are evaluated on existing embedding approaches to show the potential of joining knowledge about certain concepts across modalities in a fused concept representation.

LinkedIn data represents the world's largest online professional network, with relationships among more than 467M members, 290M jobs and 9M organizations through professional entities and attributes. This data provides the foundation of consumer products for our members and monetization products for premium members. Data value is usually measured by revenue and user engagement with the products, both of which depend on the accuracy and comprehensiveness of the data. For example, the successfulness of LinkedIn Sales Navigator is determined by how accurately it finds the right decision makers in a company for salespeople to contact, and how many such candidates are discovered. Knowledge derived from LinkedIn data needs to be represented without ambiguity in a machine-legible way.

Which authors of this paper are endorsers? Disable MathJax (What is MathJax?)

Probabilistic topic models could be used to extract low-dimension topics from document collections. However, such models without any human knowledge often produce topics that are not interpretable. In recent years, a number of knowledge-based topic models have been proposed, but they could not process fact-oriented triple knowledge in knowledge graphs. Knowledge graph embeddings, on the other hand, automatically capture relations between entities in knowledge graphs. In this paper, we propose a novel knowledge-based topic model by incorporating knowledge graph embeddings into topic modeling. By combining latent Dirichlet allocation, a widely used topic model with knowledge encoded by entity vectors, we improve the semantic coherence significantly and capture a better representation of a document in the topic space. Our evaluation results will demonstrate the effectiveness of our method.

More and more users prefer to ask their technical questions online. For machines, understanding a question is nontrivial. Current approaches lack explicit background knowledge.In this paper, we introduce a novel technical question understanding approach to recommending probable solutions to users. First, a knowledge graph is constructed which contains abundant technical information, and an augmented knowledge graph is built on the basis of the knowledge graph, to link the knowledge graph and documents. Then we develop a light weight question driven mechanism to select candidate documents. To improve the online performance, we propose an index-based random walk to support the online search. We use comprehensive experiments to evaluate the effectiveness of our approach on a large scale of real-world query logs. Our system outperforms main-stream search engine and the state-of-art information retrieval methods. Meanwhile, extensive experiments confirm the efficiency of our index-based online search mechanism.

Knowledge graph embedding represents entities and relations in knowledge graph as low-dimensional, continuous vectors, and thus enables knowledge graph compatible with machine learning models. Though there have been a variety of models for knowledge graph embedding, most methods merely concentrate on the fact triples, while supplementary textual descriptions of entities and relations have not been fully employed. To this end, this paper proposes the semantic space projection (SSP) model which jointly learns from the symbolic triples and textual descriptions. Our model builds interaction between the two information sources, and employs textual descriptions to discover semantic relevance and offer precise semantic embedding. Extensive experiments show that our method achieves substantial improvements against baselines on the tasks of knowledge graph completion and entity classification.

Knowledge graphs play a significant role in many intelligent systems such as semantic search and recommendation systems. Recent works in this area of knowledge graph embeddings such as TransE, TransH and TransR have shown extremely competitive and promising results in relational learning. In this paper, we propose a novel extension of the translational embedding model to solve three main problems of the current models. Firstly, translational models are highly sensitive to hyperparameters such as margin and learning rate. Secondly, the translation principle only allows one spot in vector space for each golden triplet. Thus, congestion of entities and relations in vector space may reduce precision. Lastly, the current models are not able to handle dynamic data especially the introduction of new unseen entities/relations or removal of triplets. In this paper, we propose Parallel Universe TransE (puTransE), an adaptable and robust adaptation of the translational model. Our approach non-parametrically estimates the energy score of a triplet from multiple embedding spaces of structurally and semantically aware triplet selection. Our proposed approach is simple, robust and parallelizable. Our experimental results show that our proposed approach outperforms TransE and many other embedding methods for link prediction on knowledge graphs on both public benchmark dataset and a real world dynamic dataset.

With the large volume of new information created every day, determining the validity of information in a knowledge graph and filling in its missing parts are crucial tasks for many researchers and practitioners. To address this challenge, a number of knowledge graph completion methods have been developed using low-dimensional graph embeddings. Although researchers continue to improve these models using an increasingly complex feature space, we show that simple changes in the architecture of the underlying model can outperform state-of-the-art models without the need for complex feature engineering. In this work, we present a shared variable neural network model called ProjE that fills-in missing information in a knowledge graph by learning joint embeddings of the knowledge graph’s entities and edges, and through subtle, but important, changes to the standard loss function. In doing so, ProjE has a parameter size that is smaller than 11 out of 15 existing methods while performing 37% better than the current-best method on standard datasets. We also show, via a new fact checking task, that ProjE is capable of accurately determining the veracity of many declarative statements.

Distributed knowledge representation learning (KRL) methods encode both entities and relations in knowledge graphs (KG) in a lower-dimensional semantic space, which model relatively dense knowledge graphs well and greatly improve the performance of knowledge graph completion and knowledge reasoning. However, existing KRL methods including Trans(E, H, R, D and Sparse) hardly obtain comparative performances on sparse KGs where most of entities and relations have very low frequencies. Furthermore, all existing methods target at KRL on one knowledge graph independently. The embeddings of different KGs are independent with each other. In this paper, we propose a novel cross-knowledge-graph (cross-KG) KRL method which learns embeddings for two different KGs simultaneously. Through projecting semantic related entities and relations in two KGs to a uniform semantic space, our method could learn better embeddings for sparse KGs by incorporating information from another relatively larger and denser KG. The learned embeddings are also helpful for downstream cross-KGs or cross-linguals tasks like ontology alignment. The experiment results show that our method could significantly outperform corresponding baseline methods on knowledge graph completion on single KG and cross-KG entity prediction and mapping tasks.

With the large volume of new information created every day, determining the validity of information in a knowledge graph and filling in its missing parts are crucial tasks for many researchers and practitioners. To address this challenge, a number of knowledge graph completion methods have been developed using low-dimensional graph embeddings. Although researchers continue to improve these models using an increasingly complex feature space, we show that simple changes in the architecture of the underlying model can outperform state-of-the-art models without the need for complex feature engineering. In this work, we present a shared variable neural network model called ProjE that fills-in missing information in a knowledge graph by learning joint embeddings of the knowledge graph's entities and edges, and through subtle, but important, changes to the standard loss function. In doing so, ProjE has a parameter size that is smaller than 11 out of 15 existing methods while performing 37% better than the current-best method on standard datasets. We also show, via a new fact checking task, that ProjE is capable of accurately determining the veracity of many declarative statements. Knowledge Graphs (KGs) have become a crucial resource for many tasks in machine learning, data mining, and artificial intelligence applications including question answering [34], entity disambiguation [7], named entity linking [14], fact checking [32], and link prediction [28] to name a few.