Cyril Allauzen


pdf bib
Federated Learning of N-Gram Language Models
Mingqing Chen | Ananda Theertha Suresh | Rajiv Mathews | Adeline Wong | Cyril Allauzen | Françoise Beaufays | Michael Riley
Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)

We propose algorithms to train production-quality 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. We propose to train a recurrent neural network language model using the decentralized FederatedAveraging algorithm and to approximate this federated model server-side with an n-gram model that can be deployed to devices for fast inference. Our technical contributions include ways of handling large vocabularies, algorithms to correct capitalization errors in user data, and efficient finite state transducer algorithms to convert word language models to word-piece language models and vice versa. The n-gram language models trained with federated learning are compared to n-grams trained with traditional server-based algorithms using A/B tests on tens of millions of users of a virtual keyboard. Results are presented for two languages, American English and Brazilian Portuguese. This work demonstrates that high-quality n-gram language models can be trained directly on client mobile devices without sensitive training data ever leaving the devices.

pdf bib
On the Compression of Lexicon Transducers
Marco Cognetta | Cyril Allauzen | Michael Riley
Proceedings of the 14th International Conference on Finite-State Methods and Natural Language Processing

In finite-state language processing pipelines, a lexicon is often a key component. It needs to be comprehensive to ensure accuracy, reducing out-of-vocabulary misses. However, in memory-constrained environments (e.g., mobile phones), the size of the component automata must be kept small. Indeed, a delicate balance between comprehensiveness, speed, and memory must be struck to conform to device requirements while providing a good user experience.In this paper, we describe a compression scheme for lexicons when represented as finite-state transducers. We efficiently encode the graph of the transducer while storing transition labels separately. The graph encoding scheme is based on the LOUDS (Level Order Unary Degree Sequence) tree representation, which has constant time tree traversal for queries while being information-theoretically optimal in space. We find that our encoding is near the theoretical lower bound for such graphs and substantially outperforms more traditional representations in space while remaining competitive in latency benchmarks.


pdf bib
Transliterated Mobile Keyboard Input via Weighted Finite-State Transducers
Lars Hellsten | Brian Roark | Prasoon Goyal | Cyril Allauzen | Françoise Beaufays | Tom Ouyang | Michael Riley | David Rybach
Proceedings of the 13th International Conference on Finite State Methods and Natural Language Processing (FSMNLP 2017)


pdf bib
Distributed representation and estimation of WFST-based n-gram models
Cyril Allauzen | Michael Riley | Brian Roark
Proceedings of the SIGFSM Workshop on Statistical NLP and Weighted Automata


pdf bib
Pushdown Automata in Statistical Machine Translation
Cyril Allauzen | Bill Byrne | Adrià de Gispert | Gonzalo Iglesias | Michael Riley
Computational Linguistics, Volume 40, Issue 3 - September 2014


pdf bib
Smoothed marginal distribution constraints for language modeling
Brian Roark | Cyril Allauzen | Michael Riley
Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)


pdf bib
The OpenGrm open-source finite-state grammar software libraries
Brian Roark | Richard Sproat | Cyril Allauzen | Michael Riley | Jeffrey Sorensen | Terry Tai
Proceedings of the ACL 2012 System Demonstrations


pdf bib
Hierarchical Phrase-based Translation Representations
Gonzalo Iglesias | Cyril Allauzen | William Byrne | Adrià de Gispert | Michael Riley
Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing


pdf bib
Expected Sequence Similarity Maximization
Cyril Allauzen | Shankar Kumar | Wolfgang Macherey | Mehryar Mohri | Michael Riley
Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics


pdf bib
OpenFst: An Open-Source, Weighted Finite-State Transducer Library and its Applications to Speech and Language
Michael Riley | Cyril Allauzen | Martin Jansche
Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Tutorial Abstracts


pdf bib
Statistical Modeling for Unit Selection in Speech Synthesis
Mehryar Mohri | Cyril Allauzen | Michael Riley
Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL-04)

pdf bib
General Indexation of Weighted Automata - Application to Spoken Utterance Retrieval
Cyril Allauzen | Mehryar Mohri | Murat Saraclar
Proceedings of the Workshop on Interdisciplinary Approaches to Speech Indexing and Retrieval at HLT-NAACL 2004


pdf bib
Generalized Algorithms for Constructing Statistical Language Models
Cyril Allauzen | Mehryar Mohri | Brian Roark
Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics