Related papers: A New Method for Knowledge Representation in Exper…

By design, large language models (LLMs) are static general-purpose models, expensive to retrain or update frequently. As they are increasingly adopted for knowledge-intensive tasks, it becomes evident that these design choices lead to…

This paper presents an overview of scientific modeling and discusses the complementary strengths and weaknesses of ML methods for scientific modeling in comparison to process-based models. It also provides an introduction to the current…

Knowledge graph embedding (KGE) is a technique that enhances knowledge graphs by addressing incompleteness and improving knowledge retrieval. A limitation of the existing KGE models is their underutilization of ontologies, specifically the…

As the interest in the representation of context dependent knowledge in the Semantic Web has been recognized, a number of logic based solutions have been proposed in this regard. In our recent works, in response to this need, we presented…

Knowledge representation and reasoning systems represent knowledge as collections of facts and rules. KRRs can represent complex concepts and relations, and they can query and manipulate information in sophisticated ways. Unfortunately, the…

In this lecture I discuss some aspects of MKM, Mathematical Knowledge Management, with particuar emphasis on information storage and information retrieval.

Large Language Models (LLMs) have demonstrated remarkable success in various tasks such as natural language understanding, text summarization, and machine translation. However, their general-purpose nature often limits their effectiveness…

Automated decision making is often complicated by the complexity of the knowledge involved. Much of this complexity arises from the context sensitive variations of the underlying phenomena. We propose a framework for representing…

Class-incremental learning requires a learning system to continually learn knowledge of new classes and meanwhile try to preserve previously learned knowledge of old classes. As current state-of-the-art methods based on Vision-Language…

The goal is to take a closer look at progress of knowledge engineering in the field of Semantic Web. Along with theory of Knowledge Representation (KR) and knowledge processing methods such as Description Logic (DL), reasoning mechanisms…

Competency modeling is widely used in human resource management to select, develop, and evaluate talent. However, traditional expert-driven approaches rely heavily on manual analysis of large volumes of interview transcripts, making them…

Recommender systems play a fundamental role in web applications in filtering massive information and matching user interests. While many efforts have been devoted to developing more effective models in various scenarios, the exploration on…

Expert System is developed as consulting service for users spread or public requires affordable access. The Internet has become a medium for such services, but presence of mobile devices make the access becomes more widespread by utilizing…

In the last few years, the interest in knowledge bases has grown exponentially in both the research community and the industry due to their essential role in AI applications. Entity alignment is an important task for enriching knowledge…

Knowledge graphs (KGs) have become important auxiliary information for helping recommender systems obtain a good understanding of user preferences. Despite recent advances in KG-based recommender systems, existing methods are prone to…

Knowledge graph embedding has recently become a popular way to model relations and infer missing links. In this paper, we present a group theoretical perspective of knowledge graph embedding, connecting previous methods with different group…

Knowledge distillation typically involves transferring knowledge from a Large Language Model (LLM) to a Smaller Language Model (SLM). However, in tasks such as text matching, fine-tuned smaller models often yield more effective…

The goal of text generation is to make machines express in human language. It is one of the most important yet challenging tasks in natural language processing (NLP). Since 2014, various neural encoder-decoder models pioneered by Seq2Seq…

Knowledge representation has been a central aim of AI since its inception. Symbolic Knowledge Graphs (KGs) and neural Large Language Models (LLMs) can both represent knowledge. KGs provide highly accurate and explicit knowledge…

Knowledge management (KM) involves collecting, organizing, storing, and disseminating information to improve decision-making, innovation, and performance. Implementing KM at scale has become essential for organizations to effectively…