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 2006.11405cs.CVcs.CLcs.LGcs.MMcs.SDeess.AS
收藏

M2P2:使用自适应融合的多模态说服力预测

M2P2: Multimodal Persuasion Prediction using Adaptive Fusion

Dartmouth College(达特茅斯学院);Harvard University(哈佛大学);Georgia Institute of Technology(佐治亚理工学院);Stanford University(斯坦福大学);Northwestern University(西北大学)

Chongyang Bai, Haipeng Chen, Srijan Kumar, Jure Leskovec, V. S. Subrahmanian

摘要:

在对抗性环境中识别有说服力的演讲者是一项关键任务。在全国大选中,政治家们希望有有说服力的演讲者代表他们竞选。当一家公司面临负面宣传时,他们希望在对手批评他们的情况下,为自己的立场聘请有说服力的倡导者。辩论是这些对抗性说服形式的共同平台。本文解决了两个问题:辩论结果预测(DOP)问题预测谁赢得了辩论,而说服力预测(IPP)问题的强度预测的投票数的变化之前和之后的发言人发言。虽然DOP以前已经研究过,但我们是第一个研究IPP的人。过去关于DOP的研究未能利用多模态数据的两个重要方面:1)多模态通常在语义上对齐,以及2)不同的模态可以提供不同的预测信息。我们的M2 P2(多模态说服力预测)框架是第一个使用多模态(声学,视觉,语言)数据来解决IPP问题的框架。为了利用不同模态的对齐,同时保持它们提供的线索的多样性,M2 P2设计了一种新的自适应融合学习框架,该框架融合了从两个模块获得的嵌入-一个对齐模块,提取模态之间的共享信息,一个异质性模块,在三个单独训练的单峰参考模型的指导下学习不同模态的权重。我们在为DOP设计的流行IQ 2US数据集上测试M2 P2。我们还为IPP引入了一个新的数据集QPS(来自中国热门的辩论电视节目Qipashuo)。M2 P2在两个数据集上的表现都明显优于4个最近的基线。

英文摘要:

Identifying persuasive speakers in an adversarial environment is a critical task. In a national election, politicians would like to have persuasive speakers campaign on their behalf. When a company faces adverse publicity, they would like to engage persuasive advocates for their position in the presence of adversaries who are critical of them. Debates represent a common platform for these forms of adversarial persuasion. This paper solves two problems: the Debate Outcome Prediction (DOP) problem predicts who wins a debate while the Intensity of Persuasion Prediction (IPP) problem predicts the change in the number of votes before and after a speaker speaks. Though DOP has been previously studied, we are the first to study IPP. Past studies on DOP fail to leverage two important aspects of multimodal data: 1) multiple modalities are often semantically aligned, and 2) different modalities may provide diverse information for prediction. Our M2P2 (Multimodal Persuasion Prediction) framework is the first to use multimodal (acoustic, visual, language) data to solve the IPP problem. To leverage the alignment of different modalities while maintaining the diversity of the cues they provide, M2P2 devises a novel adaptive fusion learning framework which fuses embeddings obtained from two modules -- an alignment module that extracts shared information between modalities and a heterogeneity module that learns the weights of different modalities with guidance from three separately trained unimodal reference models. We test M2P2 on the popular IQ2US dataset designed for DOP. We also introduce a new dataset called QPS (from Qipashuo, a popular Chinese debate TV show ) for IPP. M2P2 significantly outperforms 4 recent baselines on both datasets.

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。

↑