arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2112.13288cs.CL
收藏

立场量化:问题的定义

Stance Quantification: Definition of the Problem

Energy Institute(能源研究所)

Dilek Küçük

摘要:

姿态检测通常被定义为确定文本生成器朝向目标的位置的自动过程。在本文中,我们定义了一个与姿态检测密切相关的研究问题,即姿态量化,首次。我们定义的立场量化对包括(1)一组自然语言文本项目和(2)的目标。在姿态量化过程结束时,获得三元组,该三元组由分别朝向输入对中的目标分类为赞成、反对、都不的文本项的数量的百分比组成。本文还定义了姿态量化问题的一个重要子问题,即多目标姿态量化。我们认为,在聚合水平的立场量化可以导致在许多应用环境中的丰硕成果,此外,立场量化可能是唯一的立场相关的分析替代设置的隐私问题,防止研究人员应用通用的立场检测。

英文摘要:

Stance detection is commonly defined as the automatic process of determining the positions of text producers, towards a target. In this paper, we define a research problem closely related to stance detection, namely, stance quantification, for the first time. We define stance quantification on a pair including (1) a set of natural language text items and (2) a target. At the end of the stance quantification process, a triple is obtained which consists of the percentages of the number of text items classified as Favor, Against, Neither, respectively, towards the target in the input pair. Also defined in the current paper is a significant subproblem of the stance quantification problem, namely, multi-target stance quantification. We believe that stance quantification at the aggregate level can lead to fruitful results in many application settings, and furthermore, stance quantification might be the sole stance related analysis alternative in settings where privacy concerns prevent researchers from applying generic stance detection.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑