On the learnability and usage of acyclic probabilistic finite automata
COLT '95 Proceedings of the eighth annual conference on Computational learning theory
Statistical methods for speech recognition
Statistical methods for speech recognition
Inference of Finite-State Transducers by Using Regular Grammars and Morphisms
ICGI '00 Proceedings of the 5th International Colloquium on Grammatical Inference: Algorithms and Applications
Computational Linguistics
An empirical study of smoothing techniques for language modeling
ACL '96 Proceedings of the 34th annual meeting on Association for Computational Linguistics
Learning nonsingular phylogenies and hidden Markov models
Proceedings of the thirty-seventh annual ACM symposium on Theory of computing
Parameter estimation for probabilistic finite-state transducers
ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Observable Operator Models for Discrete Stochastic Time Series
Neural Computation
Grammatical inference as a principal component analysis problem
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Report of NEWS 2009 machine transliteration shared task
NEWS '09 Proceedings of the 2009 Named Entities Workshop: Shared Task on Transliteration
Realizations by stochastic finite automata
Journal of Computer and System Sciences
Languages as hyperplanes: grammatical inference with string kernels
Machine Learning
A discriminative model of stochastic edit distance in the form of a conditional transducer
ICGI'06 Proceedings of the 8th international conference on Grammatical Inference: algorithms and applications
IEEE Transactions on Signal Processing
Spectral learning of latent-variable PCFGs
ACL '12 Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 1
| Hi-index | 0.00 |
Finite-State Transducers (FSTs) are a popular tool for modeling paired input-output sequences, and have numerous applications in real-world problems. Most training algorithms for learning FSTs rely on gradient-based or EM optimizations which can be computationally expensive and suffer from local optima issues. Recently, Hsu et al. [13] proposed a spectral method for learning Hidden Markov Models (HMMs) which is based on an Observable Operator Model (OOM) view of HMMs. Following this line of work we present a spectral algorithm to learn FSTs with strong PAC-style guarantees. To the best of our knowledge, ours is the first result of this type for FST learning. At its core, the algorithm is simple, and scalable to large data sets. We present experiments that validate the effectiveness of the algorithm on synthetic and real data.