Adding Chit-Chats to Enhance Task-Oriented Dialogues
Authors:
- Seungwhan MoonSMSeungwhan Moon
- Honglei LiuHLHonglei Liu
Preprint
Abstract
The existing dialogue corpora and models are typically designed under two disjoint motives: while task-oriented systems focus on achieving functional goals (e.g., booking hotels), open-domain chatbots aim at making socially engaging conversations. In this work, we propose to integrate both types of systems by Adding Chit-Chats to ENhance Task-ORiented dialogues (ACCENTOR), with the goal of making virtual assistant conversations more engaging and interactive. Specifically, we propose a flexible approach for generating diverse chit-chat responses to augment task-oriented dialogues with minimal annotation effort. We then present our new chit-chat annotations to 23.8K dialogues from the popular task-oriented datasets (Schema-Guided Dialogue and MultiWOZ 2.1) and demonstrate their advantage over the originals via human evaluation. Lastly, we propose three new models for ACCENTOR explicitly trained to predict user goals and to generate contextually relevant chit-chat responses. Automatic and human evaluations show that, compared with the state-of-the-art task-oriented baseline, our models can code-switch between task and chit-chat to be more engaging, interesting, knowledgeable, and humanlike, while maintaining competitive task performance.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Recipes for Building an Open-Domain Chatbot2021
- Situated and Interactive Multimodal Conversations2020
- Few-shot Natural Language Generation for Task-Oriented Dialog2020
- The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents2020
- Can You Put it All Together: Evaluating Conversational Agents’ Ability to Blend Skills2020
- MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling2018
- Neural Belief Tracker: Data-Driven Dialogue State Tracking2017
- The Fourth Dialog State Tracking Challenge2016
- Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems2015
- The Dialog State Tracking Challenge SeriesAI Magazine, 2014