Related papers: A Grounded Approach to Modeling Generic Knowledge …

Despite serving as the foundation models for a wide range of NLP benchmarks, pre-trained language models have shown limited capabilities of acquiring implicit commonsense knowledge from self-supervision alone, compared to learning…

People acquire concepts through rich physical and social experiences and use them to understand and navigate the world. In contrast, large language models (LLMs), trained solely through next-token prediction on text, exhibit strikingly…

We investigate the generation of new concepts from combinations of properties as an artificial language develops. To do so, we have developed a new framework for conjunctive concept combination. This framework gives a semantic grounding to…

We provide a study of how induced model sparsity can help achieve compositional generalization and better sample efficiency in grounded language learning problems. We consider simple language-conditioned navigation problems in a grid world…

Compositional generalization, the ability of an agent to generalize to unseen combinations of latent factors, is easy for humans but hard for deep neural networks. A line of research in cognitive science has hypothesized a process,…

Human infants learn the names of objects and develop their own conceptual systems without explicit supervision. In this study, we propose methods for learning aligned vision-language conceptual systems inspired by infants' word learning…

A computational model for the acquisition of knowledge from encyclopedic texts is described. The model has been implemented in a program, called SNOWY, that reads unedited texts from {\em The World Book Encyclopedia}, and acquires new…

While interpretability methods identify a model's learned concepts, they overlook the relationships between concepts that make up its abstractions and inform its ability to generalize to new data. To assess whether models' have learned…

Abstraction is a desirable capability for deep learning models, which means to induce abstract concepts from concrete instances and flexibly apply them beyond the learning context. At the same time, there is a lack of clear understanding…

This work exploits translation data as a source of semantically relevant learning signal for models of word representation. In particular, we exploit equivalence through translation as a form of distributed context and jointly learn how to…

Earlier research has suggested that human infants might use statistical dependencies between speech and non-linguistic multimodal input to bootstrap their language learning before they know how to segment words from running speech. However,…

In the quest to enable robots to coexist with humans, understanding dynamic situations and selecting appropriate actions based on common sense and affordances are essential. Conventional AI systems face challenges in applying affordance, as…

We present a novel semantic framework for modeling linguistic expressions of generalization---generic, habitual, and episodic statements---as combinations of simple, real-valued referential properties of predicates and their arguments. We…

Neural language models (LMs) have been shown to capture complex linguistic patterns, yet their utility in understanding human language and more broadly, human cognition, remains debated. While existing work in this area often evaluates…

This study addresses the problem of identifying the meaning of unknown words or entities in a discourse with respect to the word embedding approaches used in neural language models. We proposed a method for on-the-fly construction and…

To perform tasks specified by natural language instructions, autonomous agents need to extract semantically meaningful representations of language and map it to visual elements and actions in the environment. This problem is called…

Word embeddings are widely used in Natural Language Processing, mainly due to their success in capturing semantic information from massive corpora. However, their creation process does not allow the different meanings of a word to be…

A wide variety of agentic AI applications - ranging from cognitive assistants for dementia patients to robotics - demand a robust memory system grounded in reality. In this paper, we propose such a memory system consisting of three…

We investigate how neural language models acquire individual words during training, extracting learning curves and ages of acquisition for over 600 words on the MacArthur-Bates Communicative Development Inventory (Fenson et al., 2007).…

Interpretability of learning-to-rank models is a crucial yet relatively under-examined research area. Recent progress on interpretable ranking models largely focuses on generating post-hoc explanations for existing black-box ranking models,…