Every time I fire a conversational designer, the performance of the dialog system goes down
Incorporating explicit domain knowledge into neural-based task-oriented dialogue systems is an effective way to reduce the need of large sets of annotated dialogues. In this paper, we investigate how the use of explicit domain knowledge of conversational designers affects the performance of neural-based dialogue systems. To support this investigation, we propose the Conversational-Logic-Injection-in-Neural-Network system (CLINN) where explicit knowledge is coded in semi-logical rules. By using CLINN, we evaluated semi-logical rules produced by a team of differently skilled conversational designers. We experimented with the Restaurant topic of the MultiWOZ dataset. Results show that external knowledge is extremely important for reducing the need of annotated examples for conversational systems. In fact, rules from conversational designers used in CLINN significantly outperform a state-of-the-art neural-based dialogue system.
Code (0)
등록된 구현이 없습니다.
Tasks
Task-Oriented Dialogue SystemsSimilar Papers 제목 키워드 기반
Every time I fire a conversational designer, the performance of the dialogue system goes down
Incorporating handwritten domain scripts into neural-based task-oriented dialogue systems may be an effective way to reduce the need for large sets of annotated dialogues. In this paper, we investigate how the use of dom…
Task-Oriented Dialogue SystemsConversational AI-Powered Design: ChatGPT as Designer, User, and Product
The recent advancements in Large Language Models (LLMs), particularly conversational LLMs like ChatGPT, have prompted changes in a range of fields, including design. This study aims to examine the capabilities of ChatGPT…
DiversityPrediction of the Most Fire-Sensitive Point in Building Structures with Differentiable Agents for Thermal Simulators
Fire safety is crucial for ensuring the stability of building structures, yet evaluating whether a structure meets fire safety requirement is challenging. Fires can originate at any point within a structure, and simulati…
Graph Neural NetworkTransfer LearningAI-based Wildfire Prevention, Detection and Suppression System
Wildfires pose a serious threat to the environment of the world. The global wildfire season length has increased by 19% and severe wildfires have besieged nations around the world. Every year, forests are burned by wildf…
Grounded verification of chemical and materials reasoning: detection is the bottleneck
Language models are moving into chemistry and materials discovery workflows, where a wrong molecular formula, space group, or formation energy can silently propagate into downstream decisions. These confabulations hide i…