• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Annual meeting of the Association for Computational Linguistics >Comparison of Diverse Decoding Methods from Conditional Language Models
【24h】

Comparison of Diverse Decoding Methods from Conditional Language Models

机译：条件语言模型不同解码方法的比较

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

While conditional language models have greatly improved in their ability to output high-quality natural language, many NLP applications benefit from being able to generate a diverse set of candidate sequences. Diverse decoding strategies aim to, within a given-sized candidate list, cover as much of the space of high-quality outputs as possible, leading to improvements for tasks that re-rank and combine candidate outputs. Standard decoding methods, such as beam search, optimize for generating high likelihood sequences rather than diverse ones, though recent work has focused on increasing diversity in these methods. In this work, we perform an extensive survey of decoding-time strategies for generating diverse outputs from conditional language models. We also show how diversity can be improved without sacrificing quality by over-sampling additional candidates, then filtering to the desired number.
机译：虽然有条件的语言模型在输出高质量自然语言的能力方面大大提高，但许多NLP应用程序受益于能够生成各种候选序列。不同的解码策略旨在在给定大小的候选名单中，尽可能多地覆盖高质量输出的空间，从而改进重新排名并组合候选输出的任务。诸如光束搜索的标准解码方法，优化用于生成高似然序列而不是多样化的序列，尽管最近的工作集中在这些方法中增加了多样性。在这项工作中，我们对从条件语言模型产生各种输出的解码时间策略进行了广泛的调查。我们还显示了如何通过过度采样额外的候选者来牺牲质量的情况如何提高多样性，然后过滤到所需的数量。

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