NeLLCom-X: A Comprehensive Neural-Agent Framework to Simulate Language Learning and Group Communication
This incremental work provides a tool for computational linguists to study language evolution through group dynamics.
The authors extended the NeLLCom framework to simulate language learning and group communication with more realistic agents, investigating the interplay between language learnability, communication pressures, and group size effects, and validated it by replicating prior findings on word-order/case-marking trade-offs.
Recent advances in computational linguistics include simulating the emergence of human-like languages with interacting neural network agents, starting from sets of random symbols. The recently introduced NeLLCom framework (Lian et al., 2023) allows agents to first learn an artificial language and then use it to communicate, with the aim of studying the emergence of specific linguistics properties. We extend this framework (NeLLCom-X) by introducing more realistic role-alternating agents and group communication in order to investigate the interplay between language learnability, communication pressures, and group size effects. We validate NeLLCom-X by replicating key findings from prior research simulating the emergence of a word-order/case-marking trade-off. Next, we investigate how interaction affects linguistic convergence and emergence of the trade-off. The novel framework facilitates future simulations of diverse linguistic aspects, emphasizing the importance of interaction and group dynamics in language evolution.