Abstract Information on the Internet is fragmented and presented in different data sources,
which makes automatic knowledge harvesting and understanding formidable for machines …

Whereas people learn many different types of knowledge from diverse experiences over
many years, and become better learners over time, most current machine learning systems …

Humor is a pervasive feature of everyday social interactions that might be leveraged to
improve human–robot interactions (HRI). Our goal is to evaluate how the use of humor can …

In this survey, we provide an overview of the literature on knowledge graphs (KGs) in the
context of information retrieval (IR). Modern IR systems can benefit from information …

The World-Wide Web consists of a huge number of unstructured documents, but it also
contains structured data in the form of HTML tables. We extracted 14.1 billion HTML tables …

Originating from Facebook, LinkedIn, Twitter, Instagram, YouTube, and many other
networking sites, the social media shared by users and the associated metadata are …

This paper presents a method for automatically constructing a large commonsense
knowledge base, called WebChild, from Web contents. WebChild contains triples that …

Computing the pairwise semantic similarity between all words on the Web is a
computationally challenging task. Parallelization and optimizations are necessary. We …

We consider the problem of finding related tables in a large corpus of heterogenous tables.
Detecting related tables provides users a powerful tool for enhancing their tables with …

We witness an unprecedented proliferation of knowledge graphs that record millions of
entities and their relationships. While knowledge graphs are structure-flexible and content …