# A Persona-based Multi-turn Conversation Model in an Adversarial Learning Framework

## TL;DR

This paper introduces persona hredGAN, an extension of the multi-turn dialogue model that incorporates external attributes like speaker identity and sub-topics, improving response quality in multi-turn conversations.

## Contribution

The paper proposes persona hredGAN, a novel multi-turn dialogue model that integrates external attributes into the hredGAN architecture for enhanced conversational consistency.

## Key findings

- Outperforms existing models on TV drama and customer service datasets.
- Achieves lower perplexity and higher BLEU, ROUGE, and Distinct scores.
- Demonstrates improved character consistency and response relevance.

## Abstract

In this paper, we extend the persona-based sequence-to-sequence (Seq2Seq) neural network conversation model to multi-turn dialogue by modifying the state-of-the-art hredGAN architecture. To achieve this, we introduce an additional input modality into the encoder and decoder of hredGAN to capture other attributes such as speaker identity, location, sub-topics, and other external attributes that might be available from the corpus of human-to-human interactions. The resulting persona hredGAN ($phredGAN$) shows better performance than both the existing persona-based Seq2Seq and hredGAN models when those external attributes are available in a multi-turn dialogue corpus. This superiority is demonstrated on TV drama series with character consistency (such as Big Bang Theory and Friends) and customer service interaction datasets such as Ubuntu dialogue corpus in terms of perplexity, BLEU, ROUGE, and Distinct n-gram scores.