arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.06351cs.CLcs.CY
收藏

善意文本请求中说服策略预测的弱监督层次模型

Weakly-Supervised Hierarchical Models for Predicting Persuasive Strategies in Good-faith Textual Requests

Jiaao Chen, Diyi Yang

摘要:

建模说服性语言有可能更好地促进我们的决策过程。尽管其重要性,说服的计算建模仍处于起步阶段,主要是由于缺乏基准数据集,可以提供说服策略的定量标签,以加快这一研究路线。为此,我们引入了一个大规模的多领域的文本语料库建模的说服策略在善意的文本请求。此外,我们设计了一个层次化的弱监督潜变量模型,可以利用部分标记的数据来预测每个句子的相关说服策略,其中监督来自整体文档级标签和非常有限的文档级标签。实验结果表明,我们提出的方法优于现有的半监督基线显着。我们已在https://github.com/GT-SALT/Persuasion_Strategy_WVAE上公开发布了我们的代码。

英文摘要:

Modeling persuasive language has the potential to better facilitate our decision-making processes. Despite its importance, computational modeling of persuasion is still in its infancy, largely due to the lack of benchmark datasets that can provide quantitative labels of persuasive strategies to expedite this line of research. To this end, we introduce a large-scale multi-domain text corpus for modeling persuasive strategies in good-faith text requests. Moreover, we design a hierarchical weakly-supervised latent variable model that can leverage partially labeled data to predict such associated persuasive strategies for each sentence, where the supervision comes from both the overall document-level labels and very limited sentence-level labels. Experimental results showed that our proposed method outperformed existing semi-supervised baselines significantly. We have publicly released our code at https://github.com/GT-SALT/Persuasion_Strategy_WVAE.

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。

↑