The Effect of Efficient Messaging and Input Variability on Neural-Agent Iterated Language Learning

Lian, Yuchen; Bisazza, Arianna; Verhoef, Tessa

doi:10.18653/v1/2021.emnlp-main.794

Cited by 4 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Emergent Communication ( EmCom ) studies focus on the evolution of communication systems among interactive agents, drawing from linguistics ( Hurford, 2014 ) and human science ( Linell, 2009 ). Research covers language emergence in human-human scenario ( Okumura et al, 2023 ), and multi-agent systems, with studies examining population heterogeneity ( Rita et al, 2022a ), messaging efficiency ( Lian et al, 2021 ), grammatical structures ( Manning et al, 2020 ), language and agent co-evolution ( Dagan et al, 2021 ), and the development of hierarchical reference systems ( Ohmer et al, 2022 ).…”

Section: Related Workmentioning

confidence: 99%

Emergent communication of multimodal deep generative models based on Metropolis-Hastings naming game

Hoang,

Taniguchi,

Hagiwara

et al. 2024

Front. Robot. AI

View full text Add to dashboard Cite

Deep generative models (DGM) are increasingly employed in emergent communication systems. However, their application in multimodal data contexts is limited. This study proposes a novel model that combines multimodal DGM with the Metropolis-Hastings (MH) naming game, enabling two agents to focus jointly on a shared subject and develop common vocabularies. The model proves that it can handle multimodal data, even in cases of missing modalities. Integrating the MH naming game with multimodal variational autoencoders (VAE) allows agents to form perceptual categories and exchange signs within multimodal contexts. Moreover, fine-tuning the weight ratio to favor a modality that the model could learn and categorize more readily improved communication. Our evaluation of three multimodal approaches - mixture-of-experts (MoE), product-of-experts (PoE), and mixture-of-product-of-experts (MoPoE)–suggests an impact on the creation of latent spaces, the internal representations of agents. Our results from experiments with the MNIST + SVHN and Multimodal165 datasets indicate that combining the Gaussian mixture model (GMM), PoE multimodal VAE, and MH naming game substantially improved information sharing, knowledge formation, and data reconstruction.

show abstract

Section: Related Workmentioning

confidence: 99%

Emergent communication of multimodal deep generative models based on Metropolis-Hastings naming game

Hoang,

Taniguchi,

Hagiwara

et al. 2024

Front. Robot. AI

View full text Add to dashboard Cite

show abstract

“…They experiment with additional learning biases to promote DNN preference for more efficient communication systems. Similarly, Lian et al (2021) describe LSTM simulations in which the network tends to preserve the distribution patterns observed in the training data, rather than to maximise efficiency of communication.…”

Section: Linguistic Universalsmentioning

confidence: 99%

Assessing the Strengths and Weaknesses of Large Language Models

Lappin

2023

J of Log Lang and Inf

View full text Add to dashboard Cite

The transformers that drive chatbots and other AI systems constitute large language models (LLMs). These are currently the focus of a lively discussion in both the scientific literature and the popular media. This discussion ranges from hyperbolic claims that attribute general intelligence and sentience to LLMs, to the skeptical view that these devices are no more than “stochastic parrots”. I present an overview of some of the weak arguments that have been presented against LLMs, and I consider several of the more compelling criticisms of these devices. The former significantly underestimate the capacity of transformers to achieve subtle inductive inferences required for high levels of performance on complex, cognitively significant tasks. In some instances, these arguments misconstrue the nature of deep learning. The latter criticisms identify significant limitations in the way in which transformers learn and represent patterns in data. They also point out important differences between the procedures through which deep neural networks and humans acquire knowledge of natural language. It is necessary to look carefully at both sets of arguments in order to achieve a balanced assessment of the potential and the limitations of LLMs.

show abstract