Related papers: Modeling natural language emergence with integral …

When trained on language data, do transformers learn some arbitrary computation that utilizes the full capacity of the architecture or do they learn a simpler, tree-like computation, hypothesized to underlie compositional meaning systems…

Word embedding techniques heavily rely on the abundance of training data for individual words. Given the Zipfian distribution of words in natural language texts, a large number of words do not usually appear frequently or at all in the…

Humans generally use natural language to communicate task requirements to each other. Ideally, natural language should also be usable for communicating goals to autonomous machines (e.g., robots) to minimize friction in task specification.…

Information systems experience an ever-growing volume of unstructured data, particularly in the form of textual materials. This represents a rich source of information from which one can create value for people, organizations and…

The dependence with text length of the statistical properties of word occurrences has long been considered a severe limitation quantitative linguistics. We propose a simple scaling form for the distribution of absolute word frequencies…

Language models are typically trained to predict the next token in a sequence. Here, we explore an alternative predictive principle from reinforcement learning: Successor Representations (SRs), which model the expected discounted…

As neural language models approach human performance on NLP benchmark tasks, their advances are widely seen as evidence of an increasingly complex understanding of syntax. This view rests upon a hypothesis that has not yet been empirically…

A centerpiece of the ever-popular reinforcement learning from human feedback (RLHF) approach to fine-tuning autoregressive language models is the explicit training of a reward model to emulate human feedback, distinct from the language…

Languages are shaped by the inductive biases of their users. Using a classical referential game, we investigate how artificial languages evolve when optimised for inductive biases in humans and large language models (LLMs) via Human-Human,…

As a core element of culture, images transform perception into structured representations and undergo evolution similar to natural languages. Given that visual input accounts for 60% of human sensory experience, it is natural to ask whether…

The joint probability distribution of many degrees of freedom in biological systems, such as firing patterns in neural networks or antibody sequence composition in zebrafish, often follow Zipf's law, where a power law is observed on a…

Evolution is a fundamental process that shapes the biological world we inhabit, and reinforcement learning is a powerful tool used in artificial intelligence to develop intelligent agents that learn from their environment. In recent years,…

Zipf's law of abbreviation, the tendency of more frequent words to be shorter, is one of the most solid candidates for a linguistic universal, in the sense that it has the potential for being exceptionless or with a number of exceptions…

Despite the recent successes of deep learning in natural language processing (NLP), there remains widespread usage of and demand for techniques that do not rely on machine learning. The advantage of these techniques is their…

Recently, there has been a great deal of research in emergent communication on artificial agents interacting in simulated environments. Recent studies have revealed that, in general, emergent languages do not follow the compositionality…

In many situations, communication between agents is a critical component of cooperative multi-agent systems, however, it can be difficult to learn or evolve. In this paper, we investigate a simple way in which the emergence of communication…

Artificial agents that learn to communicate in order to accomplish a given task acquire communication protocols that are typically opaque to a human. A large body of work has attempted to evaluate the emergent communication via various…

This paper proposes a framework for modeling sound change that combines deep learning and iterative learning. Acquisition and transmission of speech is modeled by training generations of Generative Adversarial Networks (GANs) on unannotated…

Likelihood training and maximization-based decoding result in dull and repetitive generated texts even when using powerful language models (Holtzman et al., 2019). Adding a loss function for regularization was shown to improve text…

Training agents to communicate with one another given task-based supervision only has attracted considerable attention recently, due to the growing interest in developing models for human-agent interaction. Prior work on the topic focused…