Recent years have brought about a renewed interest in commonsense representation and reasoning the field of natural language understanding. The development new knowledge graphs (CSKG) has been central to these advances as their diverse facts can be used referenced by machine learning models for tackling challenging tasks. At same time, there remain questions quality coverage resources due massi...

Generative commonsense reasoning which aims to empower machines generate sentences with the capacity of over a set concepts is critical bottleneck for text generation. Even state-of-the-art pre-trained language generation models struggle at this task and often produce implausible anomalous sentences. One reason that they rarely consider incorporating knowledge graph can provide rich relational ...

Many Artificial Intelligence tasks need large amounts of commonsense knowledge. Because obtaining this knowledge through machine learning would require a huge amount of data, a better alternative is to elicit it from people through human computation. We consider the sentiment classification task, where knowledge about the contexts that impact word polarities is crucial, but hard to acquire from...

The introduction and ever-growing size of the transformer deep-learning architecture have had a tremendous impact not only in field natural language processing but also other fields. transformer-based models contributed to renewed interest commonsense knowledge due abilities deep learning models. Recent literature has focused on analyzing embedded within pre-trained parameters these embedding m...

Relation prediction among entities in images is an important step scene graph generation (SGG), which further impacts various visual understanding and reasoning tasks. Existing SGG frameworks, however, require heavy training yet are incapable of modeling unseen (i.e., zero-shot) triplets. In this work, we stress that such incapability due to the lack commonsense reasoning, i.e., ability associa...

For an artificial system to act sensibly in the real world, it must know about that world, and it must be able to use its knowledge effectively. The common knowledge about the world that is possessed by every schoolchild and the methods for making obvious inferences from this knowledge are called common sense in both humans and computers. Almost every type of intelligent task — natural language...

Open Mind Common Sense is a knowledge acquisition system designed to acquire commonsense knowledge from the general public over the web. We describe and evaluate our first fielded system, which enabled the construction of a 400,000 assertion commonsense knowledge base. We then discuss how our second-generation system addresses weaknesses discovered in the first. The new system acquires facts, d...

While the quality and robustness of animation techniques for virtual human have improved greatly over the past couple of decades, techniques for improving their intelligence have not kept pace. Ideally, agents would be smart without being all-knowing and their future behaviors would be affected by their acquired knowledge just as with their real human counterparts. In this paper we present a me...

Speakers often refer to context only implicitly when using language. The utterance “it’s warm outside” could signal it’s warm relative to other days of the year or just relative to the current season (e.g., it’s warm for winter). Warm vaguely conveys that the temperature is high relative to some contextual comparison class, but little is known about how a listener decides upon such a standard o...

To score well in RTE3, and even more so to create good justifications for entailments, substantial lexical and world knowledge is needed. With this in mind, we present an analysis of a sample of the RTE3 positive entailment pairs, to identify where and what kinds of world knowledge are needed to fully identify and justify the entailment, and discuss several existing resources and their capacity...