Related papers: Generating new concepts with hybrid neuro-symbolic…

The ability to combine linguistic guidance from others with direct experience is central to human development, enabling safe and rapid learning in new environments. How do people integrate these two sources of knowledge, and how might AI…

It is quite exceptional, if it ever happens, that a new conceptual domain be built from scratch. Usually, it is developed and mastered in interaction, both positive and negative, with other more operational existing domains. Few reasoning…

What does it mean to create a new concept, rather than retrieve a familiar one? Repeatedly sampling a generative model at the same prompt produces variations with similar styles and typical content. We propose that creativity is the…

In a real-world setting, visual recognition systems can be brought to make predictions for images belonging to previously unknown class labels. In order to make semantically meaningful predictions for such inputs, we propose a two-step…

An important open question in the use of large language models for knowledge-intensive tasks is how to effectively integrate knowledge from three sources: the model's parametric memory, external structured knowledge, and external…

We present a new perspective on neural knowledge base (KB) embeddings, from which we build a framework that can model symbolic knowledge in the KB together with its learning process. We show that this framework well regularizes previous…

Developing inherently interpretable models for prediction has gained prominence in recent years. A subclass of these models, wherein the interpretable network relies on learning high-level concepts, are valued because of closeness of…

A hallmark of human intelligence is the ability to adapt to new situations, by applying learned rules to new content (systematicity) and thereby enabling an open-ended number of inferences and actions (generativity). Here, we propose that…

Recent developments in transformer-based language models have allowed them to capture a wide variety of world knowledge that can be adapted to downstream tasks with limited resources. However, what pieces of information are understood in…

This paper presents a novel approach to the acquisition of language models from corpora. The framework builds on Cobweb, an early system for constructing taxonomic hierarchies of probabilistic concepts that used a tabular, attribute-value…

This paper proposes a novel learning architecture for acquiring generalizable high-level symbolic skills from a few unlabeled low-level skill trajectory demonstrations. The architecture involves neural networks for symbol discovery and…

The last decade has seen huge progress in the development of advanced machine learning models; however, those models are powerless unless human users can interpret them. Here we show how the mind's construction of concepts and meaning can…

Humans possess the capability to reason at an abstract level and to structure information into abstract categories, but the underlying neural processes have remained unknown. Experimental evidence has recently emerged for the organization…

As machine learning models increase in scale and complexity, obtaining sufficient training data has become a critical bottleneck due to acquisition costs, privacy constraints, and data scarcity in specialised domains. While synthetic data…

Trust is central to human social interactions, manifesting in actions that make one vulnerable to another. We argue that trust will thus depend on the decision-making processes that arise in neural systems. Building on advances in the…

Current open-domain neural semantics parsers show impressive performance. However, closer inspection of the symbolic meaning representations they produce reveals significant weaknesses: sometimes they tend to merely copy character sequences…

Understanding how humans and AI systems interpret ambiguous visual stimuli offers critical insight into the nature of perception, reasoning, and decision-making. This paper examines image labeling performance across human participants and…

Arguments in favor of injecting symbolic knowledge into neural architectures abound. When done right, constraining a sub-symbolic model can substantially improve its performance and sample complexity and prevent it from predicting invalid…

Neuro-symbolic artificial intelligence is a novel area of AI research which seeks to combine traditional rules-based AI approaches with modern deep learning techniques. Neuro-symbolic models have already demonstrated the capability to…

Text representations using neural word embeddings have proven effective in many NLP applications. Recent researches adapt the traditional word embedding models to learn vectors of multiword expressions (concepts/entities). However, these…