mlsanityData to 14 Oct 2026

Factors Influencing the Emergence of Dependency Length Minimization in Neural Agent Simulations

arXiv 2609.06025 ↗First posted 5 Sep 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Given various grammatical options, language users prefer the word order choice that reduces the overall length of syntactic dependencies, a principle known as dependency length minimization (DLM). The origins of this preference remain an open question, particularly whether it originates from constraints on efficient information processing. Computational simulations provide a powerful approach to identifying the factors influencing the emergence of linguistic phenomena. However, previous simulations of DLM have not examined realistic interaction contexts and have produced mixed results. The present study investigates the emergence of DLM in artificial languages using a recently proposed language learning and communication framework based on recurrent neural networks (RNNs). In this framework, agents are trained to speak and interpret artificial languages and then use these languages to communicate. Using this framework, we study the impact of several factors related to processing limitations in a communicative setting, such as noise during listening, limited speaker capacity, and incremental sentence processing. Our results reveal a complex interplay among these factors in shaping word order preferences in neural agents. Specifically, in the full meaning space, agents regularize toward a single dominant word order, while in the half meaning space they show a short-before-long preference that only aligns with DLM in verb-initial languages. A consistent DLM preference emerges only when agents are subject to incremental processing pressure. These findings suggest that limitations in human cognitive processing may indeed play a role in shaping DLM. Our findings provide insights into the conditions under which neural models replicate human-like preferences and highlight the challenges of designing emergent communication models that capture human cognitive biases in language processing.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 42 of its 116 references that are in the map. First posted on arXiv 5 Sep 2026.

Builds on

42 of 116 references.

References · 42

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  3. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  4. 2019Compositionality decomposed: how do neural networks generalise?cited by 265
  5. 2018Recasting Gradient-Based Meta-Learning as Hierarchical Bayescited by 180
  6. 2015A Theoretically Grounded Application of Dropout in Recurrent Neural Networkscited by 161
  7. 2022Why Does Surprisal From Larger Transformer-Based Language Models Provide a Poorer Fit to Human Reading Times?cited by 113
  8. 2020Compositionality and Generalization in Emergent Languagescited by 103
  9. 2022What Artificial Neural Networks Can Tell Us About Human Language Acquisitioncited by 99
  10. 2016Edinburgh Neural Machine Translation Systems for WMT 16cited by 76
  11. 2020Compositional Languages Emerge in a Neural Iterated Learning Modelcited by 75
  12. 2023Contrasting Linguistic Patterns in Human and LLM-Generated News Textcited by 62
30 more
  1. 2019Anti-efficient encoding in emergent communicationcited by 59
  2. 2023Modeling rapid language learning by distilling Bayesian priors into artificial neural networkscited by 42
  3. 2020"LazImpa": Lazy and Impatient neural agents learn to communicate efficientlycited by 23
  4. 2022Emergent Communication for Understanding Human Language Evolution: What's Missing?cited by 23
  5. 2023How to Plant Trees in Language Models: Data and Architectural Effects on the Emergence of Syntactic Inductive Biasescited by 23
  6. 2023How poor is the stimulus? Evaluating hierarchical generalization in neural networks trained on child-directed speechcited by 22
  7. 2023A Language Model with Limited Memory Capacity Captures Interference in Human Sentence Processingcited by 22
  8. 2021Emergent Discrete Communication in Semantic Spacescited by 20
  9. 2019Word-order biases in deep-agent emergent communicationcited by 18
  10. 2023A Cross-Linguistic Pressure for Uniform Information Density in Word Ordercited by 17
  11. 2020The optimality of syntactic dependency distancescited by 15
  12. 2024Linear Recency Bias During Training Improves Transformers' Fit to Reading Timescited by 14
  13. 2019Anti dependency distance minimization in short sequences. A graph theoretic approachcited by 13
  14. 2021The Emergence of the Shape Bias Results from Communicative Efficiencycited by 13
  15. 2021Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communicationcited by 12
  16. 2023Communication Drives the Emergence of Language Universals in Neural Agents: Evidence from the Word-order/Case-marking Trade-offcited by 12
  17. 2018Do RNNs learn human-like abstract word order preferences?cited by 10
  18. 2022Crosslinguistic word order variation reflects evolutionary pressures of dependency and information localitycited by 10
  19. 2023Cultural evolution via iterated learning and communication explains efficient color naming systemscited by 10
  20. 2024Searching for Structure: Investigating Emergent Communication with Large Language Modelscited by 10
  21. 2025Developmentally-plausible Working Memory Shapes a Critical Period for Language Acquisitioncited by 10
  22. 2017The placement of the head that maximizes predictability. An information theoretic approachcited by 9
  23. 2024NeLLCom-X: A Comprehensive Neural-Agent Framework to Simulate Language Learning and Group Communicationcited by 8
  24. 2025Meta-Learning Neural Mechanisms rather than Bayesian Priorscited by 8
  25. 2019Focus on What's Informative and Ignore What's not: Communication Strategies in a Referential Gamecited by 7
  26. 2020Gating creates slow modes and controls phase-space complexity in GRUs and LSTMscited by 7
  27. 2021The Effect of Efficient Messaging and Input Variability on Neural-Agent Iterated Language Learningcited by 6
  28. 2024The optimal placement of the head in the noun phrase. The case of demonstrative, numeral, adjective and nouncited by 5
  29. 2025Simulating the Emergence of Differential Case Marking with Communicating Neural-Network Agentscited by 5
  30. 2025NeLLCom-Lex: A Neural-agent Framework to Study the Interplay between Lexical Systems and Language Usecited by 2

Built on by

Not cited yet.