Phase transition on a context-sensitive random language model with short range interactions

TL;DR

This study demonstrates that phase transitions in language models can occur due to intrinsic linguistic properties, even with only short-range interactions, challenging the notion that such transitions require long-range dependencies.

Contribution

The paper constructs a context-sensitive language model with short-range interactions and shows it exhibits phase transitions, highlighting their linguistic origin.

Findings

Phase transition occurs in a short-range interaction language model.

The model belongs to the class of context-sensitive grammars.

Finite-temperature phase transitions are driven by language's intrinsic properties.

Abstract

Since the random language model was proposed by E. DeGiuli [Phys. Rev. Lett. 122, 128301], language models have been investigated intensively from the viewpoint of statistical mechanics. Recently, the existence of a Berezinskii--Kosterlitz--Thouless transition was numerically demonstrated in models with long-range interactions between symbols. In statistical mechanics, it has long been known that long-range interactions can induce phase transitions. Therefore, it has remained unclear whether phase transitions observed in language models originate from genuinely linguistic properties that are absent in conventional spin models. In this study, we construct a random language model with short-range interactions and numerically investigate its statistical properties. Our model belongs to the class of context-sensitive grammars in the Chomsky hierarchy and allows explicit reference to contexts. We find that a phase transition occurs even when the model refers only to contexts whose length remains constant with respect to the sentence length. This result indicates that finite-temperature phase transitions in language models are genuinely induced by the intrinsic nature of language, rather than by long-range interactions.