Colin de la Higuera: Grammatical inference: learning automata and grammars

By Walter Daelemans. Machine Translation, 2010

375 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

RNN Architecture Learning with Sparse Regularization (2019, background): “5 The One can treat the numbers and sizes of WF-SAs as hyperparameters (Oncina et al., 1993; Ron et al., 1994; de la Higuera, 2010; Schwartz et al., 2018).”
Compositional Generalization via Neural-Symbolic Stack Machines (2020, methodology): “Faced with this challenge similar to unsupervised parsing and grammar induction [2, 11, 5], we leverage the similarities between the execution traces to induce the latent categorical information.”
Towards Synthesizing Complex Programs From Input-Output Examples (2017, background): “In contrast, in this work, we are interested in learning context-free languages (Chomsky, 1956), which is much more challenging than learning regular languages (De la Higuera, 2010).”
Interactive POMDPs with finite-state models of other agents (2017, background): “PDFCs are related to transducers in the context of grammar learning [28].”
Auction optimization using regression trees and linear models as integer programs (2014, neutral): “Language models such as deterministic automata [7] are too powerful since th ey can model every possible sequence independently and therefore require too muc h data to learn accurately.”