Adding Chit-Chat to Enhance Task-Oriented Dialogues
| Autor: | Stephen Roller, Eunjoon Cho, Claire Cardie, Seungwhan Moon, Paul A. Crook, Becka Silvert, Bing Liu, Kai Sun, Honglei Liu, Zhiguang Wang |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Focus (computing) Computer Science - Computation and Language Data collection Computer science 02 engineering and technology Remote assistance Task (project management) Annotation Human–computer interaction 0202 electrical engineering electronic engineering information engineering Task oriented 020201 artificial intelligence & image processing Baseline (configuration management) Computation and Language (cs.CL) |
| Zdroj: | NAACL-HLT |
| DOI: | 10.48550/arxiv.2010.12757 |
| Popis: | 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-Chat to ENhance Task-ORiented dialogues (ACCENTOR), with the goal of making virtual assistant conversations more engaging and interactive. Specifically, we propose a Human AI collaborative data collection approach for generating diverse chit-chat responses to augment task-oriented dialogues with minimal annotation effort. We then present our new chit-chat-based annotations to 23.8K dialogues from two 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 adding chit-chat to task-oriented dialogues, 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. Comment: To appear in NAACL-HLT 2021 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|