The natural stability of autonomous morphology

• URL: http://arxiv.org/abs/2411.03811v1
• Date: Wed, 06 Nov 2024 10:14:58 GMT
• Title: The natural stability of autonomous morphology
• Authors: Erich Round, Louise Esher, Sacha Beniamine,
• Abstract summary: We propose an explanation for the resilience of autonomous morphology. Dissociative evidence creates a repulsion dynamic which prevents morphomic classes from collapsing. We show that autonomous morphology, far from being unnatural' (e.g. citealtAronoff), is rather the natural (rational) process of inference applied to inflectional systems.
• Score: 0.0
• License:
• Abstract: Autonomous morphology, such as inflection class systems and paradigmatic distribution patterns, is widespread and diachronically resilient in natural language. Why this should be so has remained unclear given that autonomous morphology imposes learning costs, offers no clear benefit relative to its absence and could easily be removed by the analogical forces which are constantly reshaping it. Here we propose an explanation for the resilience of autonomous morphology, in terms of a diachronic dynamic of attraction and repulsion between morphomic categories, which emerges spontaneously from a simple paradigm cell filling process. Employing computational evolutionary models, our key innovation is to bring to light the role of `dissociative evidence', i.e., evidence for inflectional distinctiveness which a rational reasoner will have access to during analogical inference. Dissociative evidence creates a repulsion dynamic which prevents morphomic classes from collapsing together entirely, i.e., undergoing complete levelling. As we probe alternative models, we reveal the limits of conditional entropy as a measure for predictability in systems that are undergoing change. Finally, we demonstrate that autonomous morphology, far from being `unnatural' (e.g. \citealt{Aronoff1994}), is rather the natural (emergent) consequence of a natural (rational) process of inference applied to inflectional systems.

Related papers

• Sequential Representation Learning via Static-Dynamic Conditional Disentanglement [58.19137637859017]
  This paper explores self-supervised disentangled representation learning within sequential data, focusing on separating time-independent and time-varying factors in videos. We propose a new model that breaks the usual independence assumption between those factors by explicitly accounting for the causal relationship between the static/dynamic variables. Experiments show that the proposed approach outperforms previous complex state-of-the-art techniques in scenarios where the dynamics of a scene are influenced by its content.
  arXiv  Detail & Related papers  (2024-08-10T17:04:39Z)
• Representation Surgery: Theory and Practice of Affine Steering [72.61363182652853]
  Language models often exhibit undesirable behavior, e.g., generating toxic or gender-biased text. One natural (and common) approach to prevent the model from exhibiting undesirable behavior is to steer the model's representations. This paper investigates the formal and empirical properties of steering functions.
  arXiv  Detail & Related papers  (2024-02-15T00:20:30Z)
• Spontaneous localisation from a coarse-grained deterministic and non-unitary dynamics [0.0]
  Collapse of the wave function appears to violate the quantum superposition principle as well as deterministic evolution. Objective collapse models propose a dynamical explanation for this phenomenon, by making a non-unitary and norm-preserving modification to the Schr"odinger equation.
  arXiv  Detail & Related papers  (2023-05-11T10:32:23Z)
• Feedback-induced interactive dynamics: unitary but dissipative evolution [0.0]
  We show that measurement feedback and temporal discretization can give rise to a new type of quantum dynamics characterized by unitary but dissipative evolution. A nonequilibrium steady state with spontaneous symmetry breaking is revealed in a zero-dimensional (single-qubit) system.
  arXiv  Detail & Related papers  (2022-11-17T02:05:10Z)
• Growing Isotropic Neural Cellular Automata [63.91346650159648]
  We argue that the original Growing NCA model has an important limitation: anisotropy of the learned update rule. We demonstrate that cell systems can be trained to grow accurate asymmetrical patterns through either of two methods.
  arXiv  Detail & Related papers  (2022-05-03T11:34:22Z)
• The role of attraction-repulsion dynamics in simulating the emergence of inflectional class systems [0.0]
  Ackerman & Malouf present a model in which inflectional systems reduce in disorder through the action of an attraction-only dynamic. Here we emphasise that: (1) Attraction-only models cannot evolve the structured diversity which characterises true inflectional systems, because they inevitably remove all variation; and (2) Models with both attraction and repulsion enable the emergence of systems that are strikingly reminiscent of morphomic structure such as inflection classes.
  arXiv  Detail & Related papers  (2021-11-16T13:39:26Z)
• Natural-gradient learning for spiking neurons [0.0]
  In many normative theories of synaptic plasticity, weight updates implicitly depend on the chosen parametrization of the weights. We propose that plasticity instead follows natural gradient descent.
  arXiv  Detail & Related papers  (2020-11-23T20:26:37Z)
• Gradient Starvation: A Learning Proclivity in Neural Networks [97.02382916372594]
  Gradient Starvation arises when cross-entropy loss is minimized by capturing only a subset of features relevant for the task. This work provides a theoretical explanation for the emergence of such feature imbalance in neural networks.
  arXiv  Detail & Related papers  (2020-11-18T18:52:08Z)
• Why Adversarial Interaction Creates Non-Homogeneous Patterns: A Pseudo-Reaction-Diffusion Model for Turing Instability [10.933825676518195]
  We observe Turing-like patterns in a system of neurons with adversarial interaction. We present a pseudo-reaction-diffusion model to explain the mechanism that may underlie these phenomena.
  arXiv  Detail & Related papers  (2020-10-01T16:09:22Z)
• Euclideanizing Flows: Diffeomorphic Reduction for Learning Stable Dynamical Systems [74.80320120264459]
  We present an approach to learn such motions from a limited number of human demonstrations. The complex motions are encoded as rollouts of a stable dynamical system. The efficacy of this approach is demonstrated through validation on an established benchmark as well demonstrations collected on a real-world robotic system.
  arXiv  Detail & Related papers  (2020-05-27T03:51:57Z)
• Paradigm Completion for Derivational Morphology [48.405826282007]
  derivational morphology has been an overlooked problem in NLP. We introduce the task of derivational paradigm completion as a parallel to inflectional paradigm completion. We show that state-of-the-art neural models are able to learn a range of derivation patterns, and outperform a non-neural baseline by 16.4%.
  arXiv  Detail & Related papers  (2017-08-30T07:55:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.