arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1905.01992cs.CLcs.LGstat.ML
收藏

一个基于角色的多轮对话模型的对抗性学习框架

An Adversarial Learning Framework For A Persona-Based Multi-Turn Dialogue Model

Capital One Conversation Research(第一资本对话研究部)

Oluwatobi Olabiyi, Anish Khazane, Alan Salimov, Erik T. Mueller

摘要:

在本文中,我们扩展了基于人物的序列到序列(Seq2Seq)神经网络会话模型的多轮对话场景,通过修改最先进的hredGAN架构,同时捕获话语属性,如说话人身份,对话主题,说话人的情绪等。我们还探索了两种方法来实现条件预测:(1)phredGAN_a,一种将属性表示作为额外输入传递到传统对抗性预测中的系统,以及(2)phredGAN_d,一种除了对抗性预测之外还协同预测生成输入话语的属性的双预测系统。为了证明phredGAN优于personalSeq2Seq模型的性能,我们使用两个会话数据集进行了实验,即Ubuntu对话语料库(UDC)和Big Bang Theory和Friends的电视剧成绩单。性能比较是相对于各种量化措施以及众包的人的评价。我们还探索了在具有许多但弱属性模态的数据集(例如Big Bang Theory和Friends)和具有很少但强属性模态的数据集(Ubuntu数据集中的客户代理交互)上使用phredGAN变体的权衡。

英文摘要:

In this paper, we extend the persona-based sequence-to-sequence (Seq2Seq) neural network conversation model to a multi-turn dialogue scenario by modifying the state-of-the-art hredGAN architecture to simultaneously capture utterance attributes such as speaker identity, dialogue topic, speaker sentiments and so on. The proposed system, phredGAN has a persona-based HRED generator (PHRED) and a conditional discriminator. We also explore two approaches to accomplish the conditional discriminator: (1) phredGAN_a, a system that passes the attribute representation as an additional input into a traditional adversarial discriminator, and (2) phredGAN_d, a dual discriminator system which in addition to the adversarial discriminator, collaboratively predicts the attribute(s) that generated the input utterance. To demonstrate the superior performance of phredGAN over the persona Seq2Seq model, we experiment with two conversational datasets, the Ubuntu Dialogue Corpus (UDC) and TV series transcripts from the Big Bang Theory and Friends. Performance comparison is made with respect to a variety of quantitative measures as well as crowd-sourced human evaluation. We also explore the trade-offs from using either variant of phredGAN on datasets with many but weak attribute modalities (such as with Big Bang Theory and Friends) and ones with few but strong attribute modalities (customer-agent interactions in Ubuntu dataset).

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。

↑