Domain-specific knowledge graphs: A survey

Knowledge graph fusion for smart systems: A Survey

Full-fledged enterprise information can be a great weapon in investment analysis. However, enterprise information is scattered in different databases and websites. The information from a single source is incomplete and also suffers from noise. It is not an easy task to integrate and utilize information from diverse sources in real business scenarios. In this paper, we present an approach to build knowledge graphs (KGs) by exploiting semantic technologies to reconcile the data from diverse sources incrementally. We build a national-wide enterprise KG which incorporates information about 40,000,000 enterprises in China. We also provide querying about enterprises and data visualization capabilities as well as novel investment analysis scenarios, including finding an enterprise’s real controllers, innovative enterprise analysis, enterprise path discovery and so on. The KG and its applications are currently used by two securities companies in their investment banking and investment consulting businesses.

Building and Exploring an Enterprise Knowledge Graph for Investment Analysis

Knowledge Graphs capture the semantic relations between real-world entities and can thus, allow end-users to explore different aspects of an entity of interest by traversing through the edges in the graph Most of the state-of-the-art methods in entity recommendation are limited in the sense that they allow users to search only in the immediate neighborhood of the entity of interest This is majorly due to efficiency reasons as the search space increases exponentially as we move further away from the entity of interest in the graph Often, users perform the search task in the context of an information need and we investigate the role this context can play in overcoming the scalability issue and improving knowledge graph exploration Intuitively, only a small subset of entities in the graph are relevant to a users' interest We show how can we efficiently select this sub-set by utilizing contextual clues and using graph-theoretic measures to further re-rank this set to offer highly relevant graph exploration capabilities to end-users

Know Thy Neighbors, and More!: Studying the Role of Context in Entity Recommendation

We address the problem of finding descriptive explanations of facts stored in a knowledge graph. This is important in high-risk domains such as healthcare, intelligence, etc. where users need additional information for decision making and is especially crucial for applications that rely on automatically constructed knowledge graphs where machine-learned systems extract facts from an input corpus and working of the extractors is opaque to the end-user. We follow an approach inspired from information retrieval and propose a simple, yet effective and efficient solution that takes into account passage level as well as document level properties to produce a ranked list of passages describing a given input relation. We test our approach using Wikidata as the knowledge base and Wikipedia as the source corpus and report results of user studies conducted to study the effectiveness of our proposed model.

That’s Interesting, Tell Me More! Finding Descriptive Support Passages for Knowledge Graph Relationships

Competitive intelligence, one of the key factors of enterprise risk management and decision support, depends on knowledge bases that contain a large amount of competitive information. A variety of finance websites have collected competitive information manually, which can be used as knowledge bases. Yahoo! Finance is one of the largest and most successful finance websites among them. However, they have problems of incompleteness, lack of competitive domain, and not-in-time updating. Wikipedia, which was built with collective wisdom and contains plenty of useful information in various forms, can solve the above-mentioned problems effectively, thus helping build a more comprehensive knowledge base. In this paper, we propose a novel semi-supervised approach to identify competitor information and competitive domain from Wikipedia based on a multi-strategy learning algorithm. More precisely, we leverage seeds of competition between companies and competition between products to distantly supervise the learning process to find text patterns in free texts. Considering that competitive information can be inferred from events, we design a learning-based method to determine event description sentences. The whole process is iteratively performed. The experimental results show the effectiveness of our approach. Moreover, the results extracted from Wikipedia supplement 14,000 competitor pairs and 8,000 competitive domains between rival companies to Yahoo! Finance.

Lijuan Xue

Papers

Building and Exploring an Enterprise Knowledge Graph for Investment Analysis

Bootstrapping Yahoo! Finance by Wikipedia for Competitor Mining