Adapting Task-Oriented Dialogue Models for Email Conversations

TL;DR

This paper introduces EMToD, a transfer learning framework that adapts dialogue models for long-form email conversations, significantly improving intent detection accuracy in complex, multi-intent scenarios.

Contribution

The paper presents a novel transfer learning framework, EMToD, enabling the adaptation of dialogue models to long email conversations for better intent detection.

Findings

EMToD improves intent detection by 45% over pre-trained language models.

EMToD outperforms pre-trained dialogue models by 30%.

Framework is modular and adaptable to future model developments.

Abstract

Intent detection is a key part of any Natural Language Understanding (NLU) system of a conversational assistant. Detecting the correct intent is essential yet difficult for email conversations where multiple directives and intents are present. In such settings, conversation context can become a key disambiguating factor for detecting the user's request from the assistant. One prominent way of incorporating context is modeling past conversation history like task-oriented dialogue models. However, the nature of email conversations (long form) restricts direct usage of the latest advances in task-oriented dialogue models. So in this paper, we provide an effective transfer learning framework (EMToD) that allows the latest development in dialogue models to be adapted for long-form conversations. We show that the proposed EMToD framework improves intent detection performance over pre-trained language models by 45% and over pre-trained dialogue models by 30% for task-oriented email conversations. Additionally, the modular nature of the proposed framework allows plug-and-play for any future developments in both pre-trained language and task-oriented dialogue models.