Related papers: Deep Reinforcement Learning for Dialogue Generatio…

For task-oriented dialog systems, training a Reinforcement Learning (RL) based Dialog Management module suffers from low sample efficiency and slow convergence speed due to the sparse rewards in RL.To solve this problem, many strategies…

Pre-trained language models based on general text enable huge success in the NLP scenario. But the intrinsical difference of linguistic patterns between general text and task-oriented dialogues makes existing pre-trained language models…

Recent progress in generative models has stimulated significant innovations in many fields, such as image generation and chatbots. Despite their success, these models often produce sketchy and misleading solutions for complex multi-agent…

The next step for intelligent dialog agents is to escape their role as silent bystanders and become proactive. Well-defined proactive behavior may improve human-machine cooperation, as the agent takes a more active role during interaction…

Dialogue Policy Learning is a key component in a task-oriented dialogue system (TDS) that decides the next action of the system given the dialogue state at each turn. Reinforcement Learning (RL) is commonly chosen to learn the dialogue…

Representing a dialog policy as a recurrent neural network (RNN) is attractive because it handles partial observability, infers a latent representation of state, and can be optimized with supervised learning (SL) or reinforcement learning…

This paper reports on progress towards building an online language learning tool to provide learners with conversational experience by using dialog systems as conversation practice partners. Our system can adapt to users' language…

In neural dialogue modeling, a neural network is trained to predict the next utterance, and at inference time, an approximate decoding algorithm is used to generate next utterances given previous ones. While this autoregressive framework…

Reinforcement learning is widely used for dialogue policy optimization where the reward function often consists of more than one component, e.g., the dialogue success and the dialogue length. In this work, we propose a structured method for…

Tuning language models for dialogue generation has been a prevalent paradigm for building capable dialogue agents. Yet, traditional tuning narrowly views dialogue generation as resembling other language generation tasks, ignoring the role…

Improving the emotional awareness of pre-trained language models is an emerging important problem for dialogue generation tasks. Although prior studies have introduced methods to improve empathetic dialogue generation, few have discussed…

Task-oriented dialogue systems are designed to achieve specific goals while conversing with humans. In practice, they may have to handle simultaneously several domains and tasks. The dialogue manager must therefore be able to take into…

Forecasting conversation derailment can be useful in real-world settings such as online content moderation, conflict resolution, and business negotiations. However, despite language models' success at identifying offensive speech present in…

Modern virtual personal assistants provide a convenient interface for completing daily tasks via voice commands. An important consideration for these assistants is the ability to recover from automatic speech recognition (ASR) and natural…

With a major focus on its history, difficulties, and promise, this research paper provides a thorough analysis of the chatbot technology environment as it exists today. It provides a very flexible chatbot system that makes use of…

Personalized alignment is essential for enabling large language models (LLMs) to engage effectively in user-centric dialogue. While recent prompt-based and offline optimization methods offer preliminary solutions, they fall short in…

We study improving social conversational agents by learning from natural dialogue between users and a deployed model, without extra annotations. To implicitly measure the quality of a machine-generated utterance, we leverage signals like…

Existing open-domain dialogue generation models are usually trained to mimic the gold response in the training set using cross-entropy loss on the vocabulary. However, a good response does not need to resemble the gold response, since there…

We investigate the task of modeling open-domain, multi-turn, unstructured, multi-participant, conversational dialogue. We specifically study the effect of incorporating different elements of the conversation. Unlike previous efforts, which…

Generating responses that are consistent with the dialogue context is one of the central challenges in building engaging conversational agents. We demonstrate that neural conversation models can be geared towards generating consistent…