Related papers: A Benchmark for Systematic Generalization in Groun…
Scene graph generation (SGG) is a sophisticated task that suffers from both complex visual features and dataset long-tail problem. Recently, various unbiased strategies have been proposed by designing novel loss functions and data balancing…
Compositional generalization is the capacity to recognize and imagine a large amount of novel combinations from known components. It is a key in human intelligence, but current neural networks generally lack such ability. This report…
We introduce GSU, a text-only grid dataset to evaluate the spatial reasoning capabilities of LLMs over 3 core tasks: navigation, object localization, and structure composition. By forgoing visual inputs, isolating spatial reasoning from…
Categories such as animal or furniture are acquired at an early age and play an important role in processing, organizing, and communicating world knowledge. Categories exist across cultures: they allow to efficiently represent the…
Allowing humans to communicate through natural language with robots requires connections between words and percepts. The process of creating these connections is called symbol grounding and has been studied for nearly three decades.…
Systematic compositionality is an essential mechanism in human language, allowing the recombination of known parts to create novel expressions. However, existing neural models have been shown to lack this basic ability in learning symbolic…
Neural networks are very powerful learning systems, but they do not readily generalize from one task to the other. This is partly due to the fact that they do not learn in a compositional way, that is, by discovering skills that are shared…
Seq2seq models have been shown to struggle with compositional generalization in semantic parsing, i.e. generalizing to unseen compositions of phenomena that the model handles correctly in isolation. We phrase semantic parsing as a two-step…
Recent advances in data-driven models for grounded language understanding have enabled robots to interpret increasingly complex instructions. Two fundamental limitations of these methods are that most require a full model of the environment…
Recent research suggests that systematic generalization in natural language understanding remains a challenge for state-of-the-art neural models such as Transformers and Graph Neural Networks. To tackle this challenge, we propose Edge…
Contemporary neural networks still fall short of human-level generalization, which extends far beyond our direct experiences. In this paper, we argue that the underlying cause for this shortcoming is their inability to dynamically and…
The contemporary visual captioning models frequently hallucinate objects that are not actually in a scene, due to the visual misclassification or over-reliance on priors that resulting in the semantic inconsistency between the visual…
Spatial reasoning, an important faculty of human cognition with many practical applications, is one of the core commonsense skills that is not purely language-based and, for satisfying (as opposed to optimal) solutions, requires some…
Estimation of density functions supported on general domains arises when the data is naturally restricted to a proper subset of the real space. This problem is complicated by typically intractable normalizing constants. Score matching…
The symbol grounding problem asks how tokens like cat can be about cats, as opposed to mere shapes manipulated in a calculus. We recast grounding from a binary judgment into an audit across desiderata, each indexed by an evaluation tuple…
Instruction-tuned large language models (LLMs) have shown strong performance on a variety of tasks; however, generalizing from synthetic to human-authored instructions in grounded environments remains a challenge for them. In this work, we…
gComm is a step towards developing a robust platform to foster research in grounded language acquisition in a more challenging and realistic setting. It comprises a 2-d grid environment with a set of agents (a stationary speaker and a…
While a great effort has concerned the development of fully integrated modular understanding systems, few researches have focused on the problem of unifying existing linguistic formalisms with cognitive processing models. The Situated…
Though linguistic knowledge emerges during large-scale language model pretraining, recent work attempt to explicitly incorporate human-defined linguistic priors into task-specific fine-tuning. Infusing language models with syntactic or…
In this paper, we propose a globally normalized model for context-free grammar (CFG)-based semantic parsing. Instead of predicting a probability, our model predicts a real-valued score at each step and does not suffer from the label bias…