Using Multi-Encoder Fusion Strategies to Improve Personalized Response Selection
Using Multi-Encoder Fusion Strategies to Improve Personalized Response Selection
复制标题
DOI：
10.48550/arxiv.2208.09601
复制
发表时间：
2022-08
期刊：
影响因子：
--
通讯作者：
Souvik Das;Sougata Saha;R. Srihari
中科院分区：
文献类型：
--
作者：
Souvik Das;Sougata Saha;R. Srihari
个性化响应选择系统通常基于人物角色。然而，角色和同理心之间存在相关性，这些系统没有很好地探索这一点。此外，当选择矛盾或偏离主题的响应时，对对话上下文的忠实度就会下降。本文试图通过提出一套融合策略来解决这些问题，这些策略捕获人物角色、情感和话语蕴含信息之间的相互作用。对 Persona-Chat 数据集的消融研究表明，结合情感和蕴涵可以提高响应选择的准确性。我们结合我们的融合策略和概念流编码来训练基于 BERT 的模型，该模型在 hit@1（top-1 准确率）方面优于之前的方法，在原始角色上优于之前的方法 2.3%，在修改后的角色上优于之前的方法 1.9%，在 Persona-Chat 数据集上实现了新的最先进的性能
Personalized response selection systems are generally grounded on persona. However, a correlation exists between persona and empathy, which these systems do not explore well. Also, when a contradictory or off-topic response is selected, faithfulness to the conversation context plunges. This paper attempts to address these issues by proposing a suite of fusion strategies that capture the interaction between persona, emotion, and entailment information of the utterances. Ablation studies on the Persona-Chat dataset show that incorporating emotion and entailment improves the accuracy of response selection. We combine our fusion strategies and concept-flow encoding to train a BERT-based model which outperforms the previous methods by margins larger than 2.3% on original personas and 1.9% on revised personas in terms of hits@1 (top-1 accuracy), achieving a new state-of-the-art performance on the Persona-Chat dataset