Dialogue policy learning (DPL) is a key component in a task-oriented dialogue (TOD) system. Its goal is to decide the next action of the dialogue system, given the dialogue state …
A conversational information retrieval (CIR) system is an information retrieval (IR) system with a conversational interface, which allows users to interact with the system to seek …
In this paper, we propose to formulate the task-oriented dialogue system as the purely natural language generation task, so as to fully leverage the large-scale pre-trained models …
Aligning large language models (LLMs) with human preferences is crucial for enhancing their utility in terms of helpfulness, truthfulness, safety, harmlessness, and interestingness …
Attracted by their easy-to-use interfaces and captivating benefits, conversational systems have been widely embraced by many individuals and organizations as side-by-side digital …
Q Li, H Peng, J Li, J Wu, Y Ning, L Wang… - … on Audio, Speech …, 2021 - ieeexplore.ieee.org
Event extraction is a ftask for natural language processing. Finding the roles of event arguments like event participants is essential for event extraction. However, doing so for real …
R Takanobu, R Liang, M Huang - arXiv preprint arXiv:2004.03809, 2020 - arxiv.org
Many studies have applied reinforcement learning to train a dialog policy and show great promise these years. One common approach is to employ a user simulator to obtain a large …
This article presents a hybrid approach based on a Grounded Text Generation (GTG) model to building robust task bots at scale. GTG is a hybrid model which uses a large-scale …
Y Dai, H Yu, Y Jiang, C Tang, Y Li, J Sun - arXiv preprint arXiv:2005.02233, 2020 - arxiv.org
Dialog management (DM) is a crucial component in a task-oriented dialog system. Given the dialog history, DM predicts the dialog state and decides the next action that the dialog agent …