Related papers: Reasoning about Actions and State Changes by Injec…

As humans, we can modify our assumptions about a scene by imagining alternative objects or concepts in our minds. For example, we can easily anticipate the implications of the sun being overcast by rain clouds (e.g., the street will get…

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…

Language technologies that accurately model the dynamics of events must perform commonsense reasoning. Existing work evaluating commonsense reasoning focuses on making inferences about common, everyday situations. To instead investigate the…

Natural language processing has seen rapid progress over the past decade. Due to the speed of developments, some practices get established without proper evaluation. Considering one such case and focusing on reading comprehension, we ask…

This technical note considers the sampling of outcomes that provide the greatest amount of information about the structure of underlying world models. This generalisation furnishes a principled approach to structure learning under a…

Human tackle reading comprehension not only based on the given context itself but often rely on the commonsense beyond. To empower the machine with commonsense reasoning, in this paper, we propose a Commonsense Evidence Generation and…

Generating commonsense assertions within a given story context remains a difficult task for modern language models. Previous research has addressed this problem by aligning commonsense inferences with stories and training language…

A rich class of mechanism design problems can be understood as incomplete-information games between a principal who commits to a policy and an agent who responds, with payoffs determined by an unknown state of the world. Traditionally,…

A central concept in active inference is that the internal states of a physical system parametrise probability measures over states of the external world. These can be seen as an agent's beliefs, expressed as a Bayesian prior or posterior.…

Pretraining on large, semantically rich datasets is key for developing language models. Surprisingly, recent studies have shown that even synthetic data, generated procedurally through simple semantic-free algorithms, can yield some of the…

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…

Machine Learning models become increasingly proficient in complex tasks. However, even for experts in the field, it can be difficult to understand what the model learned. This hampers trust and acceptance, and it obstructs the possibility…

One of the central aims of neuroscience is to reliably predict the behavioral response of an organism using its neural activity. If possible, this implies we can causally manipulate the neural response and design brain-computer-interface…

Learning from demonstrations has gained increasing interest in the recent past, enabling an agent to learn how to make decisions by observing an experienced teacher. While many approaches have been proposed to solve this problem, there is…

Event commonsense reasoning requires the ability to reason about the relationship between events, as well as infer implicit context underlying that relationship. However, data scarcity makes it challenging for language models to learn to…

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…

We present a behavioral definition of an agent's perceived implication that uniquely identifies a subjective state-space representing her view of a decision problem, and which may differ from the modeler's. By examining belief updating…

Entities and events are crucial to natural language reasoning and common in procedural texts. Existing work has focused either exclusively on entity state tracking (e.g., whether a pan is hot) or on event reasoning (e.g., whether one would…

Complex reasoning over text requires understanding and chaining together free-form predicates and logical connectives. Prior work has largely tried to do this either symbolically or with black-box transformers. We present a middle ground…

The capability of imagining internally with a mental model of the world is vitally important for human cognition. If a machine intelligent agent can learn a world model to create a "dream" environment, it can then internally ask what-if…