首页> 外文会议>International Conference on Tools with Artificial Intelligence >Neural Network Language Models for Translation with Limited Data
【24h】

Neural Network Language Models for Translation with Limited Data

机译:具有有限数据的翻译神经网络语言模型

获取原文

摘要

In this paper we present how to estimate a continuous space Language Model with a Neural Network to be used in a Statistical Machine Translation system. We report results for an Italian-English translation task obtained on a small corpus (about 150~K tokens), that can be considered a task with a lack of training data. Different word history length included in the connectionist language model (Ngram order) and distinct continuous space representation (i.e. words appearing in the training corpus more than k times) are considered in the study. The experimental results are evaluated by means of automatic evaluation metrics correlated with fluency and adequacy of the generated translations.
机译:在本文中,我们介绍了如何在统计机器翻译系统中使用神经网络的连续空间语言模型。我们向小语料库(约150〜k代币)获得的意大利语 - 英语翻译任务报告结果,可以被视为缺乏培训数据的任务。在该研究中,考虑了在连接中语言模型(ngram order)中包含的不同词历史长度和不同的连续空间表示(即出现在训练语料库中的单词超过k次)。通过与流畅性和生成的翻译的充分性相关的自动评估度量来评估实验结果。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号