论文标题
英国手语建模的转移学习
Transfer Learning for British Sign Language Modelling
论文作者
论文摘要
自动语音识别和口语对话系统通过使用深度机器学习方法取得了重大进步。这部分是由于更大的计算能力，也是由于英语等通用语言的大量数据。相反，严重缺乏数据，以少数族裔语言的研究（包括符号语言）受到阻碍。这导致了转移学习方法的研究，从而将一种为一种语言开发的模型重复使用，作为第二语言模型的起点，该模型的资源较低。在本文中，我们研究了两种微调和替代英国手语的语言建模的转移学习技术。我们的结果表明，使用标准堆叠LSTM模型的转移学习时，困惑性有所改善，最初是使用Penn Treebank Corpus的标准英语的大型语料库进行培训
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
