相关论文: CAT: A Contextualized Conceptualization and Instan…

Recently, pretrained language models (e.g., BERT) have achieved great success on many downstream natural language understanding tasks and exhibit a certain level of commonsense reasoning ability. However, their performance on commonsense…

Commonsense knowledge is crucial for artificial intelligence systems to understand natural language. Previous commonsense knowledge acquisition approaches typically rely on human annotations (for example, ATOMIC) or text generation models…

Commonsense reasoning simulates the human ability to make presumptions about our physical world, and it is an essential cornerstone in building general AI systems. We propose a new commonsense reasoning dataset based on human's Interactive…

Neural networks lack the ability to reason about qualitative physics and so cannot generalize to scenarios and tasks unseen during training. We propose ESPRIT, a framework for commonsense reasoning about qualitative physics in natural…

Commonsense reasoning aims to empower machines with the human ability to make presumptions about ordinary situations in our daily life. In this paper, we propose a textual inference framework for answering commonsense questions, which…

The paper proposes a semantic clustering based deduction learning by mimicking the learning and thinking process of human brains. Human beings can make judgments based on experience and cognition, and as a result, no one would recognize an…

Deep learning models perform poorly on tasks that require commonsense reasoning, which often necessitates some form of world-knowledge or reasoning over information not immediately present in the input. We collect human explanations for…

Concept embeddings offer a practical and efficient mechanism for injecting commonsense knowledge into downstream tasks. Their core purpose is often not to predict the commonsense properties of concepts themselves, but rather to identify…

This paper is the second in a planned series aimed at envisioning a path to safe and beneficial artificial intelligence. Building on the conceptual insights of "Common Sense Is All You Need," we propose a more formal litmus test for common…

Many agents in real-world environments cannot reliably communicate their goals through language, including household pets, pre-verbal infants, and other non-speaking embodied agents. In such settings, intent must be inferred from incomplete…

Most benchmark datasets targeting commonsense reasoning focus on everyday scenarios: physical knowledge like knowing that you could fill a cup under a waterfall [Talmor et al., 2019], social knowledge like bumping into someone is awkward…

The human capability to reason about one domain by using knowledge of other domains has been researched for more than 50 years, but models that are formally sound and predict cognitive process are sparse. We propose a formally sound method…

Existing dense or paragraph video captioning approaches rely on holistic representations of videos, possibly coupled with learned object/action representations, to condition hierarchical language decoders. However, they fundamentally lack…

In empathetic conversations, individuals express their empathy towards others. Previous work has mainly focused on generating empathetic responses by utilizing the speaker's emotion. Besides, external commonsense knowledge has been applied…

Humans possess a remarkable ability to acquire knowledge efficiently and apply it across diverse modalities through a coherent and shared understanding of the world. Inspired by this cognitive capability, we introduce a concept-centric…

Transformer models pre-trained with a masked-language-modeling objective (e.g., BERT) encode commonsense knowledge as evidenced by behavioral probes; however, the extent to which this knowledge is acquired by systematic inference over the…

Social Commonsense Reasoning requires understanding of text, knowledge about social events and their pragmatic implications, as well as commonsense reasoning skills. In this work we propose a novel multi-head knowledge attention model that…

Most prior art in visual understanding relies solely on analyzing the "what" (e.g., event recognition) and "where" (e.g., event localization), which in some cases, fails to describe correct contextual relationships between events or leads…

As computational power has continued to increase, and sensors have become more accurate, the corresponding advent of systems that are at once cognitive and immersive has arrived. These \textit{cognitive and immersive systems} (CAISs) fall…

Commonsense knowledge (CSK) supports a variety of AI applications, from visual understanding to chatbots. Prior works on acquiring CSK, such as ConceptNet, have compiled statements that associate concepts, like everyday objects or…