arXiv subjects

Matilde Marcolli

Publications and source records attributed to Matilde Marcolli.

At least 19 recordsLinked to original sources

arXiv2026

Representation of syntax in LLMs through the lens of linear distance and similarity-aware entropy

Structural probes were introduced by Hewitt and Manning to reconstruct syntactic trees from a neural language model's latent representations. They are evaluated by calculating the proportion of syntactic tree edges correctly reconstructed over an annotated corpus (as measured by undirected unlabeled attachment score). Here, we disaggregate this measure, considering undirected attachment score by label (UASL), which assesses the reconstruction accuracy of each syntactic relation separately, establishing important differences among relations that overlap linguistic distinctions. Moreover, we identify two factors that predict most of UASL's variability across relations: (i) the mean and dispersion of the linear distance (on a log scale) between the related words, and (ii) the diversity (similarity-aware entropy) of the syntactic relation's head. These results, which hold across a range of model sizes and architectures, shed light on the degree of abstraction of the representation of syntax in language models and the dependence of such representation on geometric properties of the embedding space.

cs.CL↗

arXiv2025

Merge on workspaces as Hopf algebra Markov chain

We study the dynamical properties of a Hopf algebra Markov chain with state space the binary rooted forests with labelled leaves. This Markovian dynamical system describes the core computational process of structure formation and transformation in syntax via the Merge operation, according to Chomsky's Minimalism model of generative linguistics. The dynamics decomposes into an ergodic dynamical system with uniform stationary distribution, given by the action of Internal Merge, while the contributions of External Merge and (a minimal form of) Sideward Merge reduce to a simpler Markov chain with state space the set of partitions and with combinatorial weights. The Sideward Merge part of the dynamics prevents convergence to fully formed connected structures (trees), unless the different forms of Merge are weighted by a cost function, as predicted by linguistic theory. Results on the asymptotic behavior of the Perron-Frobenius eigenvalue and eigenvector in this weighted case, obtained in terms of an associated Perron-Frobenius problem in the tropical semiring, show that the usual cost functions (Minimal Search and Resource Restrictions) proposed in the linguistic literature do not suffice to obtain convergence to the tree structures, while an additional optimization property based on the Shannon entropy achieves the expected result for the dynamics. We also comment on the introduction of continuous parameters related to semantic embedding and other computational models, and also on some filtering of the dynamics by coloring rules that model the linguistic filtering by theta roles and phase structure, and on parametric variation and the process of parameter setting in Externalization.

math.DS↗

arXiv2025

Extension Condition "violations" and Merge optimality constraints

We analyze, using the mathematical formulation of Merge within the Strong Minimalist Thesis framework, a set of linguistic phenomena, including head-to-head movement, phrasal affixes and syntactic cliticization, verb-particle alternation, and operator-variable phenomena. These are often regarded as problematic, as violations of the Extension Condition. We show that, in fact, all of these phenomena can be explained without involving any EC violation. We first show that derivations using Sideward Merge are possible for all of these cases: these respect EC, though they involve some amount of optimality violations, with respect to Resource Restrictions cost functions, andthe amount of violation differs among these cases. We show that all the cases that involve large optimality violations can be derived in alternative ways involving neither EC nor the use of SM. The main remaining case (head-to-head movement) only involves SM with minimal violations of optimality (near equilibrium fluctuations). We analyze explicitly also the cases of multiple wh-fronting, clusters of clitics in Romance languages and possessor agreement construction in Korean, and how an explanation of these phenomena based on SM can be made compatible with the colored operad generators for phases and theta roles. We also show that the EC condition has a clear algebraic meaning in the mathematical formulation of Merge and is therefore an intrinsic structural algebraic constraint of the model, rather than an additional assumption. We also show that the minimal optimality violating SM plays a structural role in the Markovian properties of Merge, and we compare different optimality conditions coming from Minimal Search and from Resource Restriction in terms of their effect on the dynamics of the Hopf algebra Markov chain, in a simple explicit example.

cs.CL↗

arXiv2025

Adelic Models of Percolation

Models of long range percolations on lattices and on hierarchical lattices are related through the use of three intermediate geometries: a 1-parameter deformation based on the power mean function, relating lattice percolation to a percolation model governed by the toric volume form; the adelic product formula for a function field, relating the hierarchical lattice model to an adelic percolation model; and the adelic product formula for number fields that relates the toric percolation model on the lattice given by the ring of integers in the Minkowski embedding to another adelic percolation model.

math-ph↗

arXiv2025

Encoding syntactic objects and Merge operations in function spaces

We provide a mathematical argument showing that, given a representation of lexical items as functions (wavelets, for instance) in some function space, it is possible to construct a faithful representation of arbitrary syntactic objects in the same function space. This space can be endowed with a commutative non-associative semiring structure built using the second Renyi entropy. The resulting representation of syntactic objects is compatible with the magma structure. The resulting set of functions is an algebra over an operad, where the operations in the operad model circuits that transform the input wave forms into a combined output that encodes the syntactic structure. The action of Merge on workspaces is faithfully implemented as action on these circuits, through a coproduct and a Hopf algebra Markov chain. The results obtained here provide a constructive argument showing the theoretical possibility of a neurocomputational realization of the core computational structure of syntax. We also present a particular case of this general construction where this type of realization of Merge is implemented as a cross frequency phase synchronization on sinusoidal waves. This also shows that Merge can be expressed in terms of the successor function of a semiring, thus clarifying the well known observation of its similarities with the successor function of arithmetic.

cs.CL↗

arXiv2025

Hypermagmas and Colored Operads: Heads, Phases, and Theta Roles

We show that head functions on syntactic objects extend the magma structure to a hypermagma, with the c-command relation compatible with the magma operation and the m-command relation with the hypermagma. We then show that the structure of head and complement and specifier, additional modifier positions, and the structure of phases in the Extended Projection can be formulated as a bud generating system of a colored operad, in a form similar to the structure of theta roles. We also show that, due to the special form of the colored operad generators, the filtering of freely generated syntactic objects by these coloring rules can be equivalently formulated as a filtering in the course of structure formation via a colored Merge, which can in turn be related to the hypermagma structure. The rules on movement by Internal Merge with respect to phases, the Extended Projection Principle, Empty Category Principle, and Phase Impenetrability Condition are all subsumed into the form of the colored operad generators. Movement compatibilities between the phase structure and the theta roles assignments can then be formulated in terms of the respective colored operads and a transduction of colored operads.

cs.CL↗

arXiv2025

A Lie-algebraic perspective on Tree-Adjoining Grammars

We provide a novel mathematical implementation of tree-adjoining grammars using two combinatorial definitions of graphs. With this lens, we demonstrate that the adjoining operation defines a pre-Lie operation and subsequently forms a Lie algebra. We demonstrate the utility of this perspective by showing how one of our mathematical formulations of TAG captures properties of the TAG system without needing to posit them as additional components of the system, such as null-adjoining constraints and feature TAG.

cs.CL↗

arXiv2025

The Algebraic Structure of Morphosyntax

Within the context of the mathematical formulation of Merge and the Strong Minimalist Thesis, we present a mathematical model of the morphology-syntax interface. In this setting, morphology has compositional properties responsible for word formation, organized into a magma of morphological trees. However, unlike syntax, we do not have movement within morphology. A coproduct decomposition exists, but it requires extending the set of morphological trees beyond those which are generated solely by the magma, to a larger set of possible morphological inputs to syntactic trees. These participate in the formation of morphosyntactic trees as an algebra over an operad, and a correspondence between algebras over an operad. The process of structure formation for morphosyntactic trees can then be described in terms of this operadic correspondence that pairs syntactic and morphological data and the morphology coproduct. We reinterpret in this setting certain operations of Distributed Morphology as transformation that allow for flexibility in moving the boundary between syntax and morphology within the morphosyntactic objects.

cs.CL↗

arXiv2025

Theta Theory: operads and coloring

We give an explicit construction of the generating set of a colored operad that implements theta theory in the mathematical model of Minimalism in generative linguistics, in the form of a coloring algorithm for syntactic objects. We show that the coproduct operation on workspaces allows for a recursive implementation of the theta criterion. We also show that this filtering by coloring rules on structures freely formed by Merge is equivalent to a process of structure formation by a colored version of Merge: the form of the generators of the colored operad then implies the dichotomy is semantics between External and Internal Merge, where Internal Merge only moves to non-theta positions.

cs.CL↗

arXiv2024

Formal Languages and TQFTs with Defects

A construction that assigns a Boolean 1D TQFT with defects to a finite state automaton was recently developed by Gustafson, Im, Kaldawy, Khovanov, and Lihn. We show that the construction is functorial with respect to the category of finite state automata with transducers as morphisms. Certain classes of subregular languages correspond to additional cohomological structures on the associated TQFTs. We also show that the construction generalizes to context-free grammars through a categorical version of the Chomsky-Sch\"utzenberger representation theorem, due to Melli\`es and Zeilberger. The corresponding TQFTs are then described as morphisms of colored operads on an operad of cobordisms with defects.

math-ph↗

arXiv2024

Wormhole Renormalization: The gravitational path integral, holography, and a gauge group for topology change

We study the Factorization Paradox from the bottom up by adapting methods from perturbative renormalization. Just as quantum field theories are plagued with loop divergences that need to be cancelled systematically by introducing counterterms, gravitational path integrals are plagued by wormhole contributions that spoil the factorization of the holographic dual. These wormholes must be cancelled by some stringy effects in a UV complete, holographic theory of quantum gravity. In a simple model of two-dimensional topological gravity, we outline a gravitational analog of the recursive BPHZ procedure in order to systematically introduce ``counter-wormholes" which parametrize the unknown stringy effects that lead to factorization. Underlying this procedure is a Hopf algebra of symmetries which is analogous to the Connes--Kreimer Hopf algebra underlying perturbative renormalization. The group dual to this Hopf algebra acts to reorganize contributions from spacetimes with distinct topology, and can be seen as a gauge group relating various equivalent ways of constructing a factorizing gravitational path integral.

hep-th↗

arXiv2024

Explicit formulas for the Grothendieck class of $\overline{\mathcal M}_{0,n}$

We obtain explicit expressions for the class in the Grothendieck group of varieties of the moduli space of genus 0 stable curves with n marked points. This information is equivalent to the Poincar\'e polynomial; it implies explicit expressions for the Betti numbers of the moduli space in terms of Stirling numbers or, alternatively, Bernoulli numbers. The expressions are obtained by solving a differential equation characterizing the generating function for the Grothendieck class as shown in work of Yuri Manin from the 1990s. This differential equation is equivalent to S. Keel's recursion for the Betti numbers of these moduli spaces. Our proof reduces the solution to two combinatorial identities which follow from applications of Lagrange series. We also study generating functions for the individual Betti numbers. In previous work it had been shown that these functions are determined by a set of polynomials with positive rational coefficients, which are conjecturally log-concave. We verify this conjecture for many infinite families of these polynomials, corresponding to the generating functions for the $2k$-Betti numbers of the moduli spaces for all $k\le 100$. Further, studying these polynomials allows us to prove that the generating function for the Grothendieck class of the moduli spaces may be written as a series of rational functions in the Lefschetz motive and the principal branch of the Lambert W-function. We include an interpretation of the main result in terms of Stirling matrices and a discussion of the Euler characteristic of the moduli space.

math.AG↗

arXiv2024

Formal languages, spin systems, and quasicrystals

We present a categorical formalism for context-free languages with morphisms given by correspondences obtained from rational transductions. We show that D0L-systems are a special case of the correspondences that define morphisms in this category. We construct a functorial mapping to aperiodic spin chains. We then generalize this construction to a class of mildly context sensitive grammars, the multiple-context-free grammars (MCFG), with a similar functorial mapping to spin systems in higher dimensions, with Boltzmann weights describing interacting spins on vertices of hypercubes. We show that a particular motivating example for this general construction is provided by the Korepin completely integrable model on the icosahedral quasicrystal, which we construct as the spin system associated to a multiple-context-free grammar describing the geometry of the Ammann planes quasilattice. We review the main properties of this spin system, including solvability, bulk free energy, and criticality, based on results of Baxter and the known relation to the Zamolodchikov tetrahedron equation. We show that the latter has a generalization for the Boltzmannweights on hypercubes of the spin systems associated to more general MCFGs in terms of two dual cubulations of the n-simplex. We formulate analogous questions about bulk free energy and criticality for our construction of spin systems.

math-ph↗

arXiv2024

Log concavity of the Grothendieck class of $\overline{\mathcal M}_{0,n}$

Using a known recursive formula for the Grothendieck classes of the moduli spaces $\overline{\mathcal M}_{0,n}$, we prove that they satisfy an asymptotic form of ultra-log-concavity as polynomials in the Lefschetz class. We also observe that these polynomials are $\gamma$-positive. Both properties, along with numerical evidence, support the conjecture that these polynomials only have real zeros. This conjecture may be viewed as a particular case of a possible extension of a conjecture of Ferroni-Schr\"oter and Huh on Hilbert series of Chow rings of matroids. We prove asymptotic ultra-log-concavity by studying differential equations obtained from the recursion, whose solutions are the generating functions of the individual betti numbers of $\overline{\mathcal M}_{0,n}$. We obtain a rather complete description of these generating functions, determining their asymptotic behavior; their dominant term is controlled by the coefficients of the Lambert W function. The $\gamma$-positivity property follows directly from the recursion, extending the argument of Ferroni et al. proving $\gamma$-positivity for the Hilbert series of the Chow ring of matroids.

math.AG↗

arXiv2024

Spectral action and heat kernel trace for Ricci flat manifolds from stochastic flow over second quantized $L^2$-differential forms

A quantum stochastic differential equation (qsde) on Fock space over $L^2$ differential 1-forms is given from the small "time" flow of which the trace of the connection Laplacian heat kernel for the spinor endomorphism bundle can be computed over any compact Ricci-flat Riemannian manifold. The existence of the stochastic flow is established by adapting the construction from [14]. When the manifold supports a parallel spinor - Ricci-flatness is a required integrability condition for parallel spinors, the trace of Dirac Laplacian heat kernel of the spinor bundle can be recovered. For 4-manifolds, this corresponds to the spectral action, and realizes Einstein-Hilbert action as a stochastic flow.

math-ph↗

arXiv2023

Syntax-semantics interface: an algebraic model

We extend our formulation of Merge and Minimalism in terms of Hopf algebras to an algebraic model of a syntactic-semantic interface. We show that methods adopted in the formulation of renormalization (extraction of meaningful physical values) in theoretical physics are relevant to describe the extraction of meaning from syntactic expressions. We show how this formulation relates to computational models of semantics and we answer some recent controversies about implications for generative linguistics of the current functioning of large language models.

cs.CL↗

arXiv2023

Gabor frames and higher dimensional boundaries in signal analysis on manifolds

We provide a construction of Gabor frames that encode local linearizations of a signal detected on a curved smooth manifold of arbitrary dimension, with Gabor filters that can detect the presence of higher-dimensional boundaries in the manifold signal. We describe an application in configuration spaces in robotics with sharp constrains. The construction is a higher-dimensional generalization of the geometric setting developed for the study of signal analysis in the visual cortex.

eess.SP↗

arXiv2023

Old and New Minimalism: a Hopf algebra comparison

In this paper we compare some old formulations of Minimalism, in particular Stabler's computational minimalism, and Chomsky's new formulation of Merge and Minimalism, from the point of view of their mathematical description in terms of Hopf algebras. We show that the newer formulation has a clear advantage purely in terms of the underlying mathematical structure. More precisely, in the case of Stabler's computational minimalism, External Merge can be described in terms of a partially defined operated algebra with binary operation, while Internal Merge determines a system of right-ideal coideals of the Loday-Ronco Hopf algebra and corresponding right-module coalgebra quotients. This mathematical structure shows that Internal and External Merge have significantly different roles in the old formulations of Minimalism, and they are more difficult to reconcile as facets of a single algebraic operation, as desirable linguistically. On the other hand, we show that the newer formulation of Minimalism naturally carries a Hopf algebra structure where Internal and External Merge directly arise from the same operation. We also compare, at the level of algebraic properties, the externalization model of the new Minimalism with proposals for assignments of planar embeddings based on heads of trees.

cs.CL↗