@inproceedings{deshmukh2022adapting,
author = {Deshmukh, Soham and Lee, Charles},
title = {Adapting Task-Oriented Dialogue Models for Email Conversations},
booktitle = {arXiv preprint arXiv:2208.09439},
year = {2022},
month = {August},
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.},
url = {http://approjects.co.za/?big=en-us/research/publication/adapting-task-oriented-dialogue-models-for-email-conversations/},
}