Transfer Learning for British Sign Language Modelling

Abstract

Automatic speech recognition and spoken dialogue systems have made great advances through the use of deep machine learning methods. This is partly due to greater computing power but also through the large amount of data available in common languages, such as English. Conversely, research in minority languages, including sign languages, is hampered by the severe lack of data. This has led to work on transfer learning methods, whereby a model developed for one language is reused as the starting point for a model on a second language, which is less resourced. In this paper, we examine two transfer learning techniques of fine-tuning and layer substitution for language modelling of British Sign Language. Our results show improvement in perplexity when using transfer learning with standard stacked LSTM models, trained initially using a large corpus for standard English from the Penn Treebank corpus

10 pages, 3 figures

References in corpus (7)

• How transferable are features in deep neural networks?
• Regularizing and Optimizing LSTM Language Models
• Artificial Neural Networks Applied to Taxi Destination Prediction
• An Analysis of Neural Language Modeling at Multiple Scales
• Generative Deep Neural Networks for Dialogue: A Short Review
• Bidirectional American Sign Language to English Translation
• Diverse Embedding Neural Network Language Models