Towards More Human-like AI Communication: A Review of Emergent Communication Research
arXiv:2308.02541 · doi:10.1109/ACCESS.2023.3339656
Abstract
In the recent shift towards human-centric AI, the need for machines to accurately use natural language has become increasingly important. While a common approach to achieve this is to train large language models, this method presents a form of learning misalignment where the model may not capture the underlying structure and reasoning humans employ in using natural language, potentially leading to unexpected or unreliable behavior. Emergent communication (Emecom) is a field of research that has seen a growing number of publications in recent years, aiming to develop artificial agents capable of using natural language in a way that goes beyond simple discriminative tasks and can effectively communicate and learn new concepts. In this review, we present Emecom under two aspects. Firstly, we delineate all the common proprieties we find across the literature and how they relate to human interactions. Secondly, we identify two subcategories and highlight their characteristics and open challenges. We encourage researchers to work together by demonstrating that different methods can be viewed as diverse solutions to a common problem and emphasize the importance of including diverse perspectives and expertise in the field. We believe a deeper understanding of human communication is crucial to developing machines that can accurately use natural language in human-machine interactions.
25 pages, 9 figures, 2 tables
References in corpus (16)
- LLaMA: Open and Efficient Foundation Language Models
- LaMDA: Language Models for Dialog Applications
- Linguistic generalization and compositionality in modern artificial neural networks
- Discrete Autoencoders for Sequence Models
- Developmentally motivated emergence of compositional communication via template transfer
- The Emergence of Compositional Languages for Numeric Concepts Through Iterated Learning in Neural Agents
- Shaping representations through communication: community size effect in artificial learning systems
- Emergent Communication Pretraining for Few-Shot Machine Translation
- Interpretable agent communication from scratch (with a generic visual processor emerging on the side)
- Measuring non-trivial compositionality in emergent communication
- Emergent Graphical Conventions in a Visual Communication Game
- Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communication
- On (Emergent) Systematic Generalisation and Compositionality in Visual Referential Games with Straight-Through Gumbel-Softmax Estimator
- Recommendations for Systematic Research on Emergent Language
- Referential communication in heterogeneous communities of pre-trained visual deep networks
- Focus on What's Informative and Ignore What's not: Communication Strategies in a Referential Game