论文标题
使用多编码器融合策略来改善个性化响应选择
Using Multi-Encoder Fusion Strategies to Improve Personalized Response Selection
论文作者
论文摘要
个性化响应选择系统通常基于角色。但是，角色和同理心之间存在共同关联，这些系统在这些系统中并不是很好。同样，当选择矛盾或主题反应时，对对话背景的忠诚会暴跌。本文试图通过提出一套融合策略来解决这些问题，以捕捉角色，情感和话语的综合信息之间的相互作用。关于角色 - 奇特数据集的消融研究表明，结合情绪和努力可以提高响应选择的准确性。我们将融合策略和概念流编码结合在一起，以训练基于BERT的模型，该模型以先前的方法的优于原始角色大于2.3％的利润率，而修订后的角色的1.9％（前1位准确性）（前1位准确性），在Persona-Chat DataSet上实现了新的先进性能。
Personalized response selection systems are generally grounded on persona. However, there exists a co-relation between persona and empathy, which is not explored well in these systems. Also, faithfulness to the conversation context plunges when a contradictory or an off-topic response is selected. 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.
