Automatic knowledge graph construction aims at manufacturing structured human
knowledge. To this end, much effort has historically been spent extracting informative fact …

Large Language Models (LLMs) have shown extraordinary capabilities in understanding
and generating text that closely mirrors human communication. However, a primary …

Structured knowledge is important for many AI applications. Commonsense knowledge,
which is crucial for robust human-centric AI, is covered by a small number of structured …

Querying knowledge graphs (KGs) using deep learning approaches can naturally leverage
the reasoning and generalization ability to learn to infer better answers. Traditional neural …

Abstract Knowledge sharing among academics is critical for innovation and growth in higher
education institutions. However, introducing a knowledge-sharing culture can be …

Commonsense reasoning, aiming at endowing machines with a human-like ability to make
situational presumptions, is extremely challenging to generalize. For someone who barely …

The task of zero-shot commonsense question answering evaluates models on their capacity
to reason about general scenarios beyond those presented in specific datasets. Existing …

Conceptualization, or viewing entities and situations as instances of abstract concepts in
mind and making inferences based on that, is a vital component in human intelligence for …

Knowledge in NLP has been a rising trend especially after the advent of large-scale pre-
trained models. Knowledge is critical to equip statistics-based models with common sense …

Cognitive research indicates that abstraction ability is essential in human intelligence, which
remains under-explored in language models. In this paper, we present AbsPyramid, a …