paper-with-me

Papers

Congruence-based Learning of Probabilistic Deterministic Finite Automata

2024-12-12 · Matías Carrasco, Franz Mayr, Sergio Yovine

This work studies the question of learning probabilistic deterministic automata from language models. For this purpose, it focuses on analyzing the relations defined on algebraic structures over strings by equivalences and similarities on probability distributions. We introduce a congruence that extends the classical Myhill-Nerode congruence for formal languages. This new congruence is the basis for defining regularity over language models. We present an active learning algorithm that computes the quotient with respect to this congruence whenever the language model is regular. The paper also defines the notion of recognizability for language models and shows that it coincides with regularity for congruences. For relations which are not congruences, it shows that this is not the case. Finally, it discusses the impact of this result on learning in the context of language models.

📄 PDF Abstract BibTeX arXiv:2412.09760

Code (0)

등록된 구현이 없습니다.

Tasks

Active LearningLanguage ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

Probabilistic Deterministic Infinite Automata

2010-12-01 · NeurIPS 2010 12 · David Pfau, Nicholas Bartlett, Frank Wood

We propose a novel Bayesian nonparametric approach to learning with probabilistic deterministic finite automata (PDFA). We define and develop and sampler for a PDFA with an infinite number of states which we call the pro…

Learning Deterministic Weighted Automata with Queries and Counterexamples

2019-10-30 · NeurIPS 2019 12 · Gail Weiss, Yoav Goldberg, Eran Yahav

We present an algorithm for extraction of a probabilistic deterministic finite automaton (PDFA) from a given black-box language model, such as a recurrent neural network (RNN). The algorithm is a variant of the exact-lea…

Language ModelingLanguage Modelling

Mixed Nondeterministic-Probabilistic Automata: Blending graphical probabilistic models with nondeterminism

2022-01-19 · Albert Benveniste, Jean-Baptiste Raclet

Graphical models in probability and statistics are a core concept in the area of probabilistic reasoning and probabilistic programming-graphical models include Bayesian networks and factor graphs. In this paper we develo…

Probabilistic Programming

Query Learning Algorithm for Residual Symbolic Finite Automata

2019-02-20 · Kaizaburo Chubachi, Diptarama Hendrian, Ryo Yoshinaka, Ayumi Shinohara

We propose a query learning algorithm for residual symbolic finite automata (RSFAs). Symbolic finite automata (SFAs) are finite automata whose transitions are labeled by predicates over a Boolean algebra, in which a big …

Unambiguity and Fewness for Nonuniform Families of Polynomial-Size Nondeterministic Finite Automata

2023-11-16 · Tomoyuki Yamakami

Nonuniform families of polynomial-size finite automata, which are series of indexed finite automata having polynomially many inner states, are used in the past literature to solve nonuniform families of promise decision …