A Filter-Based Algorithm for Efficient Composition of Finite-State Transducers

Allauzen, Cyril; Riley, Michael; Schalkwyk, Johan

doi:10.1142/s0129054111009033

Cited by 4 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since A has backoff transitions, the generic composition algorithm of (Allauzen et al, 2011) is used with a custom composition filter that ensures the result, B, is deterministic with a well-formed backoff structure, and hence is suitable for the counting step of SampleApprox . We give an explicit description of the construction of B, from which readers familiar with Allauzen et al (2011) can infer the form of the custom composition filter.…”

Section: Morphologically Rich Languagesmentioning

confidence: 99%

Federated Learning of N-Gram Language Models

Chen

Suresh

Mathews

et al. 2019

Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)

Self Cite

View full text Add to dashboard Cite

We propose algorithms to train productionquality n-gram language models using federated learning. Federated learning is a distributed computation platform that can be used to train global models for portable devices such as smart phones. Federated learning is especially relevant for applications handling privacy-sensitive data, such as virtual keyboards, because training is performed without the users' data ever leaving their devices. While the principles of federated learning are fairly generic, its methodology assumes that the underlying models are neural networks. However, virtual keyboards are typically powered by n-gram language models for latency reasons.

show abstract

Section: Morphologically Rich Languagesmentioning

confidence: 99%

Federated Learning of N-Gram Language Models

Chen

Suresh

Mathews

et al. 2019

Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)

Self Cite

View full text Add to dashboard Cite

show abstract

“…There are several filter transducer possibilities which can be tailored for specific purposes or to improve the efficiency of the resulting model [Allauzen et al 2011]. For instance, the removal of redundant paths can be obtained by means of the epsilon-matching or by means of the epsilon-sequencing filters.…”

mentioning

confidence: 99%

Contributions to the joint segmentation and classification of sequences (My two cents on decoding and handwriting recognition)

Boquera¹

View full text Add to dashboard Cite

To my family, past, present and future, very specially to my parents and to my wife Manuela for their unconditional love and support. v 65 3.1.8 Prediction/Forecasting 65 3.1.9 Translation 65 3.1.10 Alignment 66 3.1.11 KWS, indexing, querying by example 69 3.1.12 Unsupervised term discovery 72 3.1.13 Filtering/Denoising and Smoothing 73 3.1.14 Summarization 73 3.1.15 Joint Segmentation and Classification 74 3.2 Some extensions 80 3.2.1 Several input sequences 80 3.2.2 Interactive systems 82 xv xvi Contents 3.3 Limitations, how to face them, new proposal 87 3.4 Questionnaire when faced with a new problem 91 3.5 Analysis and evaluation measures 93 3.5.1 Quality assessment 96 3.5.2 Performance 99 3.5.3 Interaction 100 3.5.4 Other measures 102 3.6 Summary and some conclusions 102 105 4.1 Some preliminary ML concepts 106 4.1.1 (Probabilistic) graphical models 115 4.2 Two stage generative model 130 4.2.1 Hierarchy for the second stage 133 4.2.2 Limitations, extensions and generalizations 137 4.3 Classical problems of two stage generative models 141 4.3.1 Probability of observation 142 4.3.2 Decoding 144 4.3.3 Model estimation 145 4.4 Some alternative models 146 4.4.1 Relationship with Dynamic Graphical Models 146 4.4.2 Fixed dimension feature segments 150 4.4.3 Estimation of frame-wise segment posteriors 155 4.4.4 Graph transformer networks 160 4.4.5 Some non-probabilistic frameworks 163 4.5 Summary and some conclusions 165 , , , 167 5.1 Introduction 167 5.2 Recognition, parsing, decoding 170 5.3 Weighted languages and semirings 172 5.4 Some formalisms 177 5.4.1 Formal/generative grammars 177 5.4.2 Finite state automata and transducers 184 5.4.3 Recurrent transition networks 187 5.5 Deriving the composition of a regular and a CF model 194 5.5.1 State-pair transducer composition 195 5.5.2 Extension to null-transitions 200 5.5.3 Extension to model reference transitions 209 5.5.4 Transformation to homogeneous epsilon form 220 5.6 Review of parsing approaches, decoders and algorithms 225 5.7 From composition to recognition/decoding 232 5.7.1 Acyclic inputs 233 5.7.2 Semiring specific optimizations 235 5.8 Summary and some conclusions 235 239 6.1 Probabilistic decompositions 242 6.1.1 Chain rule, clustering histories 243 6.1.2 Whole sentence LMs 244 6.1.3 Combining spans of the sequence 245 6

show abstract