首页> 外文会议>Workshop on new frontiers in summarization 2017 >Automatic Community Creation for Abstractive Spoken Conversation Summarization
【24h】

Automatic Community Creation for Abstractive Spoken Conversation Summarization

机译:自动社区创建,用于抽象口语对话摘要

获取原文
获取原文并翻译 | 示例

摘要

Summarization of spoken conversations is a challenging task, since it requires deep understanding of dialogs. Abstractive summarization techniques rely on linking the summary sentences to sets of original conversation sentences, i.e. communities. Unfortunately, such linking information is rarely available or requires trained anno-tators. We propose and experiment automatic community creation using cosine similarity on different levels of representation: raw text, WordNet SynSet IDs, and word embeddings. We show that the abstractive summarization systems with automatic communities significantly outperform previously published results on both English and Italian corpora.
机译:总结口头对话是一项艰巨的任务,因为它需要对对话有深刻的理解。抽象摘要技术依赖于将摘要语句链接到原始对话语句集(即社区)。不幸的是,这种链接信息很少获得或需要训练有素的注释者。我们提出并尝试在不同表示形式上使用余弦相似度来自动创建社区:原始文本,WordNet SynSet ID和单词嵌入。我们显示,具有自动社区的抽象汇总系统显着优于以前在英语和意大利语语料库上发布的结果。

著录项

  • 来源
  • 会议地点 Copenhagen(DK)
  • 作者单位

    AIL, University of Southern California, Los Angeles, CA, USA,Signals and Interactive Systems Lab, DISI, University of Trento, Trento, Italy;

    Signals and Interactive Systems Lab, DISI, University of Trento, Trento, Italy;

    Signals and Interactive Systems Lab, DISI, University of Trento, Trento, Italy;

    Department of Computer Science, University of British Columbia, Vancouver, Canada;

    Signals and Interactive Systems Lab, DISI, University of Trento, Trento, Italy;

  • 会议组织
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

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