...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Computer speech and language >On the effects of using word2vec representations in neural networks for dialogue act recognition
【24h】

On the effects of using word2vec representations in neural networks for dialogue act recognition

机译：关于在神经网络中使用word2vec表示进行对话行为识别的效果

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Dialogue act recognition is an important component of a large number of natural language processing pipelines. Many research works have been carried out in this area, but relatively few investigate deep neural networks and word embeddings. This is surprising, given that both of these techniques have proven exceptionally good in most other language-related domains. We propose in this work a new deep neural network that explores recurrent models to capture word sequences within sentences, and further study the impact of pretrained word embeddings. We validate this model on three languages: English, French and Czech. The performance of the proposed approach is consistent across these languages and it is comparable to the state-of-the-art results in English. More importantly, we confirm that deep neural networks indeed outperform a Maximum Entropy classifier, which was expected. However, and this is more surprising, we also found that standard word2vec embeddings do not seem to bring valuable information for this task and the proposed model, whatever the size of the training corpus is. We thus further analyse the resulting embeddings and conclude that a possible explanation may be related to the mismatch between the type of lexical-semantic information captured by the word2vec embeddings, and the kind of relations between words that is the most useful for the dialogue act recognition task.
机译：对话行为识别是大量自然语言处理管道的重要组成部分。在这一领域已经进行了许多研究工作，但是研究深度神经网络和词嵌入的研究相对较少。鉴于这两种技术在大多数其他与语言相关的领域中都被证明具有出色的性能，这令人惊讶。我们在这项工作中提出了一个新的深度神经网络，该网络将探索递归模型以捕获句子中的单词序列，并进一步研究预训练单词嵌入的影响。我们使用三种语言验证该模型：英语，法语和捷克语。所提出的方法在这些语言之间的性能是一致的，并且可以与英语的最新结果相媲美。更重要的是，我们确认深度神经网络的确优于预期的最大熵分类器。但是，这更令人惊讶，我们还发现，无论训练语料库的大小如何，标准的word2vec嵌入似乎都无法为该任务和建议的模型带来有价值的信息。因此，我们进一步分析了产生的嵌入，并得出结论，可能的解释可能与word2vec嵌入捕获的词汇语义信息的类型与对对话行为识别最有用的单词之间的关系类型之间的不匹配有关。任务。

著录项

  • 来源
    《Computer speech and language》 |2018年第1期|175-193|共19页
  • 作者

    Christophe Cerisara; Pavel Kral; Ladislav Lenc;

  • 作者单位

    WRIA-UMR7503, Campus Scientifique, 54506 Vandoeuvre-les-Nancy, France;

    Department of Computer Science & Engineering, Faculty of Applied Sciences, University of West Bohemia, Plzen, Czechia,NTIS - New Technologies for the Information Society, Faculty of Applied Sciences, University of West Bohemia, Plzen, Czechia;

    Department of Computer Science & Engineering, Faculty of Applied Sciences, University of West Bohemia, Plzen, Czechia,NTIS - New Technologies for the Information Society, Faculty of Applied Sciences, University of West Bohemia, Plzen, Czechia;

  • 收录信息 美国《科学引文索引》(SCI);美国《工程索引》(EI);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Dialogue act; Deep learning; LSTM; Word embeddings; Word2vec;

    机译：对话行为;深度学习;LSTM;词嵌入;Word2vec;

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