Related papers: Learning End-to-End Goal-Oriented Dialog with Maxi…
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…
We present a system that enables real-time interaction between human users and agents trained to control fighter jets in simulated 3D air combat scenarios. The agents are trained in a dedicated environment using Multi-Agent Reinforcement…
Pre-trained models have proved to be powerful in enhancing task-oriented dialog systems. However, current pre-training methods mainly focus on enhancing dialog understanding and generation tasks while neglecting the exploitation of dialog…
We present BotSIM, a data-efficient end-to-end Bot SIMulation toolkit for commercial text-based task-oriented dialog (TOD) systems. BotSIM consists of three major components: 1) a Generator that can infer semantic-level dialog acts and…
Task-oriented dialogue (TOD) system is designed to accomplish user-defined tasks through dialogues. The TOD system has progressed towards end-to-end modeling by leveraging pre-trained large language models. Fine-tuning the pre-trained…
The consistency of a response to a given post at semantic-level and emotional-level is essential for a dialogue system to deliver human-like interactions. However, this challenge is not well addressed in the literature, since most of the…
Multimodal chatbots have become one of the major topics for dialogue systems in both research community and industry. Recently, researchers have shed light on the multimodality of responses as well as dialogue contexts. This work explores…
Conversational agents have traditionally been developed for either task-oriented dialogue (TOD) or open-ended chitchat, with limited progress in unifying the two. Yet, real-world conversations naturally involve fluid transitions between…
User Satisfaction Estimation (USE) is an important yet challenging task in goal-oriented conversational systems. Whether the user is satisfied with the system largely depends on the fulfillment of the user's needs, which can be implicitly…
In this work, we propose a novel framework that integrates large language models (LLMs) with an RL-based dialogue manager for open-ended dialogue with a specific goal. By leveraging hierarchical reinforcement learning to model the…
The ultimate goal of embodied agents is to create collaborators that can interact with humans, not mere executors that passively follow instructions. This requires agents to communicate, coordinate, and adapt their actions based on human…
Task-oriented dialogue systems help users accomplish tasks such as booking a movie ticket and ordering food via conversation. Generative models parameterized by a deep neural network are widely used for next turn response generation in such…
Communication is essential for coordination among humans and animals. Therefore, with the introduction of intelligent agents into the world, agent-to-agent and agent-to-human communication becomes necessary. In this paper, we first study…
Imitation learning and instruction-following are two common approaches to communicate a user's intent to a learning agent. However, as the complexity of tasks grows, it could be beneficial to use both demonstrations and language to…
Dialogue systems have many applications such as customer support or question answering. Typically they have been limited to shallow single turn interactions. However more advanced applications such as career coaching or planning a trip…
In this paper we take the first steps in studying a new approach to synthesis of efficient communication schemes in multi-agent systems, trained via reinforcement learning. We combine symbolic methods with machine learning, in what is…
Dialogue act annotations are important to improve response generation quality in task-oriented dialogue systems. However, it can be challenging to use dialogue acts to control response generation in a generalizable way because different…
Reinforcement Learning (RL) methods have emerged as a popular choice for training an efficient and effective dialogue policy. However, these methods suffer from sparse and unstable reward signals returned by a user simulator only when a…
This proposal introduces a Dialogue Challenge for building end-to-end task-completion dialogue systems, with the goal of encouraging the dialogue research community to collaborate and benchmark on standard datasets and unified experimental…
Task assignment and scheduling algorithms are powerful tools for autonomously coordinating large teams of robotic or AI agents. However, the decisions these system make often rely on components designed by domain experts, which can be…