A Neural Conversation Generation Model via Equivalent Shared Memory Investigation

TL;DR

This paper introduces a Deep Reading Memory Network (DRMN) that leverages information from similar conversations to enhance neural conversation generation, demonstrating improved performance on justice and e-commerce datasets.

Contribution

The paper presents a novel memory network that utilizes conversation similarities for better utterance generation, advancing the state-of-the-art in neural conversation models.

Findings

DRMN outperforms existing models on large-scale datasets

Utilizing similar conversation information improves generation quality

Model effectively captures entities and relationships from related conversations

Abstract

Conversation generation as a challenging task in Natural Language Generation (NLG) has been increasingly attracting attention over the last years. A number of recent works adopted sequence-to-sequence structures along with external knowledge, which successfully enhanced the quality of generated conversations. Nevertheless, few works utilized the knowledge extracted from similar conversations for utterance generation. Taking conversations in customer service and court debate domains as examples, it is evident that essential entities/phrases, as well as their associated logic and inter-relationships can be extracted and borrowed from similar conversation instances. Such information could provide useful signals for improving conversation generation. In this paper, we propose a novel reading and memory framework called Deep Reading Memory Network (DRMN) which is capable of remembering useful information of similar conversations for improving utterance generation. We apply our model to two large-scale conversation datasets of justice and e-commerce fields. Experiments prove that the proposed model outperforms the state-of-the-art approaches.