Abstract Similarity searches on heterogeneous information networks (HINs) have attracted wide attention from both industrial and academic areas in recent years; for example, they been used friend detection social collaborator recommendation coauthor networks. The structural the HIN can be captured by multiple metapaths, people usually utilize metapaths to design methods similarity search. rich ...

Online legal document libraries, such as WorldLII, are indispensable tools for professionals to conduct research. We study how topic modeling techniques can be applied platforms facilitate searching of court judgments. Specifically, we improve search effectiveness by matching judgments queries at semantics level rather than keyword level. Also, design a system that summarizes retrieved judgment...

Abstract Dense embedding-based semantic matching is widely used in e-commerce product search to address the shortcomings of lexical such as sensitivity spelling variants. The recent advances BERT-like language model encoders, have however, not found their way realtime due strict inference latency requirement imposed on websites. While bi-encoder BERT architectures enable fast approximate neares...

The web, as we experience it nowadays, is heavily based on search engines such as Google or Yahoo!. These engines are the essential step to discover web-content that would, otherwise, only be available after too many clicks. The field of computer-science which serves as their theoretical basis is information retrieval. However, the main focus of information retrieval is on textual content, that...

Web has become an important part of our day to day lives. Whether we are trying to make an online payment or if we are trying to reserve a trip, we can do that with a click of a mouse. Web has defined the way we live. It has made our lives easier and effortless. Search engines play an important role in the current web’s infrastructure. Similarly, with the advent of semantic web, there would be ...

The semantic web not only contains resources but also includes the heterogeneous relationships among them, which is sharply distinguished from the current web. As the growth of the semantic web, specialized search techniques are of significance. In this paper, we present RSS—a framework for enabling ranked semantic search on the semantic web. In this framework, the heterogeneity of relationship...