Weighted finite automata (WFAs) are often used to represent probabilistic models, such as n-gram language models, because among other things, they are efficient for recognition tasks in time and space. The probabilistic source to be represented as a WFA, however, may come in many forms. Given a generic probabilistic model over sequences, we propose an algorithm to approximate it as a WFA such that the Kullback-Leibler divergence between the source model and the WFA target model is minimized. The proposed algorithm involves a counting step and a difference of convex optimization step, both of which can be performed efficiently. We demonstrate the usefulness of our approach on various tasks, including distilling n-gram models from neural models, building compact language models, and building open-vocabulary character models. The algorithms used for these experiments are available in an open-source software library.

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.

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.

Weighted finite automata (WFA) are often used to represent probabilistic models, such as n-gram language models, since they are efficient for recognition tasks in time and space. The probabilistic source to be represented as a WFA, however, may come in many forms. Given a generic probabilistic model over sequences, we propose an algorithm to approximate it as a weighted finite automaton such that the Kullback-Leibler divergence between the source model and the WFA target model is minimized. The proposed algorithm involves a counting step and a difference of convex optimization, both of which can be performed efficiently. We demonstrate the usefulness of our approach on some tasks including distilling n-gram models from neural models.

The use of the Latin script for text entry of South Asian languages is common, even though there is no standard orthography for these languages in the script. We explore several compact finite-state architectures that permit variable spellings of words during mobile text entry. We find that approaches making use of transliteration transducers provide large accuracy improvements over baselines, but that simpler approaches involving a compact representation of many attested alternatives yields much of the accuracy gain. This is particularly important when operating under constraints on model size (e.g., on inexpensive mobile devices with limited storage and memory for keyboard models), and on speed of inference, since people typing on mobile keyboards expect no perceptual delay in keyboard responsiveness.