Analyzing the Benefits of Domain Knowledge in Substructure Discovery

AAAI Conferences

However, scientists working with a database in their area of expertise often search for predetermined types of structures, or for structures exhibiting characteristics specific to the domain. This paper presents a method for guiding the discovery process with domain-specific knowledge.

Pragmatic Querying in Heterogeneous Knowledge Graphs

AAAI Conferences

Knowledge Graphs with rich schemas can allow for complex querying. My thesis focuses on providing accessible Knowledge using Gricean notions of Cooperative Answering as a motivation. More specifically, using Query Reformulations, Data Awareness, and a Pragmatic Context, along with the results they can become more responsive to user requirements and user context.

Bridging the Gap Between Schank and Montague

AAAI Conferences

Documents that people write to communicate with other people are rarely as precise as a formal logic. Yet people can read those documents and relate them to formal notations for science, mathematics, and computer programming. They can derive whatever information they need, reason about it, and apply it at an appropriate level of precision. Unlike theorem provers, people rely on analogies for their reasoning. Even mathematicians use analogies to discover their theorems and formal proofs to verify and codify their discoveries. This article shows how a high-speed analogy engine is used to analyze natural language texts and relate the results to both structured and unstructured representations. The degree of precision in the results depends more on the precision in the knowledge sources used to analyze the documents than on the precision of the language in the documents themselves.

The Enterprise Knowledge Graph


Best conceived of as a "company brain," this knowledge graph focuses on integrating an organization's assortment of people, skills, experiences, materials, essential company databases, and projects, which greatly improves its self-knowledge and thereby yields competitive advantage. Compiled from combing through myriad databases, including those for human resources, emails, and manifold other sources, this knowledge graph provides the foundation for a rapid, detailed assessment of what knowledge and skills a company has at its disposal--and their relation to one another. This graph is designed to create better services and is extremely specific to an organization's industry, line of business, and area of specialization. For example, Google's and Yahoo's search engine endeavors mandate that they collect knowledge about every entity or subject in the world, so they can offer the most relevant, revealing information to their users. LinkedIn's knowledge graph, on the other hand, details people's professions, resumes, and career opportunities.1 Again, the relationships between these nodes are paramount.

Weakly-supervised Knowledge Graph Alignment with Adversarial Learning Artificial Intelligence

This paper studies aligning knowledge graphs from different sources or languages. Most existing methods train supervised methods for the alignment, which usually require a large number of aligned knowledge triplets. However, such a large number of aligned knowledge triplets may not be available or are expensive to obtain in many domains. Therefore, in this paper we propose to study aligning knowledge graphs in fully-unsupervised or weakly-supervised fashion, i.e., without or with only a few aligned triplets. We propose an unsupervised framework to align the entity and relation embddings of different knowledge graphs with an adversarial learning framework. Moreover, a regularization term which maximizes the mutual information between the embeddings of different knowledge graphs is used to mitigate the problem of mode collapse when learning the alignment functions. Such a framework can be further seamlessly integrated with existing supervised methods by utilizing a limited number of aligned triples as guidance. Experimental results on multiple datasets prove the effectiveness of our proposed approach in both the unsupervised and the weakly-supervised settings.