Persuasive strategy recognition task requires the system to recognize the
adopted strategy of the persuader according to the conversation. However,
previous methods mainly focus on the contextual information, little is known
about incorporating the psychological feedback, i.e. emotion of the persuadee,
to predict the strategy. In this paper, we propose a Cross-channel Feedback
memOry Network (CFO-Net) to leverage the emotional feedback to iteratively
measure the potential benefits of strategies and incorporate them into the
contextual-aware dialogue information. Specifically, CFO-Net designs a feedback
memory module, including strategy pool and feedback pool, to obtain
emotion-aware strategy representation. The strategy pool aims to store
historical strategies and the feedback pool is to obtain updated strategy
weight based on feedback emotional information. Furthermore, a cross-channel
fusion predictor is developed to make a mutual interaction between the
emotion-aware strategy representation and the contextual-aware dialogue
information for strategy recognition. Experimental results on
\textsc{PersuasionForGood} confirm that the proposed model CFO-Net is effective
to improve the performance on M-F1 from 61.74 to 65.41.

本文提出了一个基于跨通道反馈记忆网络 (CFO-Net) 的方法，以将情感反馈任务引入到说服策略识别任务中。通过设计一个反馈记忆模块和交叉通道融合预测器，该方法将情感反馈与上下文感知的对话信息相互作用，提高了 M-F1 的性能。实验表明，CFO-Net 能够将性能从 61.74% 提高到 65.41%。

你了解我的情感吗？面向具有说服力的对话系统的情感感知策略识别

Do You Know My Emotion? Emotion-Aware Strategy Recognition towards a Persuasive Dialogue System

Persuasion aims at forming one's opinion and action via a series of
persuasive messages containing persuader's strategies. Due to its potential
application in persuasive dialogue systems, the task of persuasive strategy
recognition has gained much attention lately. Previous methods on user intent
recognition in dialogue systems adopt recurrent neural network (RNN) or
convolutional neural network (CNN) to model context in conversational history,
neglecting the tactic history and intra-speaker relation. In this paper, we
demonstrate the limitations of a Transformer-based approach coupled with
Conditional Random Field (CRF) for the task of persuasive strategy recognition.
In this model, we leverage inter- and intra-speaker contextual semantic
features, as well as label dependencies to improve the recognition. Despite
extensive hyper-parameter optimizations, this architecture fails to outperform
the baseline methods. We observe two negative results. Firstly, CRF cannot
capture persuasive label dependencies, possibly as strategies in persuasive
dialogues do not follow any strict grammar or rules as the cases in Named
Entity Recognition (NER) or part-of-speech (POS) tagging. Secondly, the
Transformer encoder trained from scratch is less capable of capturing
sequential information in persuasive dialogues than Long Short-Term Memory
(LSTM). We attribute this to the reason that the vanilla Transformer encoder
does not efficiently consider relative position information of sequence
elements.

本文旨在研究使用 Transformer 和 CRF 模型进行说服策略识别的方法，并通过实验证明该方法存在缺陷，不能很好地识别个人之间的对话关系和标签依赖关系。