Generative Conversational Networks

Alexandros Papangelis, Karthik Gopalakrishnan, Aishwarya Padmakumar, Seokhwan Kim, Gokhan Tur, Dilek Hakkani-Tur


Abstract
Inspired by recent work in meta-learning and generative teaching networks, we propose a framework called Generative Conversational Networks, in which conversational agents learn to generate their own labelled training data (given some seed data) and then train themselves from that data to perform a given task. We use reinforcement learning to optimize the data generation process where the reward signal is the agent’s performance on the task. The task can be any language-related task, from intent detection to full task-oriented conversations. In this work, we show that our approach is able to generalise from seed data and performs well in limited data and limited computation settings, with significant gains for intent detection and slot tagging across multiple datasets: ATIS, TOD, SNIPS, and Restaurants8k. We show an average improvement of 35% in intent detection and 21% in slot tagging over a baseline model trained from the seed data. We also conduct an analysis of the novelty of the generated data and provide generated examples for intent detection, slot tagging, and non-goal oriented conversations.
Anthology ID:
2021.sigdial-1.12
Volume:
Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue
Month:
July
Year:
2021
Address:
Singapore and Online
Editors:
Haizhou Li, Gina-Anne Levow, Zhou Yu, Chitralekha Gupta, Berrak Sisman, Siqi Cai, David Vandyke, Nina Dethlefs, Yan Wu, Junyi Jessy Li
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
111–120
Language:
URL:
https://aclanthology.org/2021.sigdial-1.12
DOI:
10.18653/v1/2021.sigdial-1.12
Bibkey:
Cite (ACL):
Alexandros Papangelis, Karthik Gopalakrishnan, Aishwarya Padmakumar, Seokhwan Kim, Gokhan Tur, and Dilek Hakkani-Tur. 2021. Generative Conversational Networks. In Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 111–120, Singapore and Online. Association for Computational Linguistics.
Cite (Informal):
Generative Conversational Networks (Papangelis et al., SIGDIAL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.sigdial-1.12.pdf
Video:
 https://www.youtube.com/watch?v=NL703avDlpE
Data
ATISCIFAR-10SNIPS