Strategies for training large scale neural network language models

Стратегии обучения крупномасштабных языковых моделей на основе нейронных сетей
Tomáš Mikolov, Daniel Povey, Lukáš Burget, Jaň Černocký, Anoop Deoras
2011-12-01

4-gram baseline trained on 400M tokenshash-based maximum entropy modelintegrated maxent within neural networklarge scale neural network language modelstraining data sorting by relevanceword error rate reduction on English Broadcast News
We describe how to effectively train neural network based language models on large data sets. Fast convergence during training and better overall performance is observed when the training data are sorted by their relevance. We introduce hash-based implementation of a maximum entropy model, that can be trained as a part of the neural network model. This leads to significant reduction of computational complexity. We achieved around 10% relative reduction of word error rate on English Broadcast News speech recognition task, against large 4-gram model trained on 400M tokens.
1
A hash-based implementation of a maximum entropy component can be integrated into the neural network language model.
2
Integrating the hash-based maximum entropy model substantially reduces computational complexity.
3
On English Broadcast News speech recognition, the proposed approach achieved about a 10% relative reduction in word error rate compared to a large 4-gram model trained on 400M tokens.
4
Sorting training data by relevance yields faster convergence and better overall performance for neural network language model training.

Neural network–based language models trained on large datasets

Training strategies and modifications (data sorting by relevance and hash-based max-entropy component) that improve convergence, reduce computational complexity, and lower word error rate

Publication Details
Publication Date
2011-12-01
Journal
Publisher
ISSN
Access Type
Author Information
Authors
Tomáš Mikolov
Daniel Povey
Lukáš Burget
Jaň Černocký
Anoop Deoras
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat
Make a presentation
100%