Related papers: A Modular Task-oriented Dialogue System Using a Ne…

In recent years, we are seeing considerable interest in conversational agents with the rise of large language models (LLMs). Although they offer considerable advantages, LLMs also present significant risks, such as hallucination, which…

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…

There is increasing interest in developing personalized Task-oriented Dialogue Systems (TDSs). Previous work on personalized TDSs often assumes that complete user profiles are available for most or even all users. This is unrealistic…

Sparse Mixtures of Experts (SMoE) scales model capacity without significant increases in training and inference costs, but exhibits the following two issues: (1) Low expert activation, where only a small subset of experts are activated for…

This work introduces TTS-Transducer - a novel architecture for text-to-speech, leveraging the strengths of audio codec models and neural transducers. Transducers, renowned for their superior quality and robustness in speech recognition, are…

This paper describes our submission for the End-to-end Multi-domain Task Completion Dialog shared task at the 9th Dialog System Technology Challenge (DSTC-9). Participants in the shared task build an end-to-end task completion dialog system…

To help the open-source community have a better understanding of Mixture-of-Experts (MoE) based large language models (LLMs), we train and release OpenMoE, a series of fully open-sourced and reproducible decoder-only MoE LLMs, ranging from…

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…

Existing dialogue models may encounter scenarios which are not well-represented in the training data, and as a result generate responses that are unnatural, inappropriate, or unhelpful. We propose the "Ask an Expert" framework in which the…

Task-oriented dialog (TOD) systems typically manage structured knowledge (e.g. ontologies and databases) to guide the goal-oriented conversations. However, they fall short of handling dialog turns grounded on unstructured knowledge (e.g.…

Mixture-of-experts (MoE) is gaining increasing attention due to its unique properties and remarkable performance, especially for language tasks. By sparsely activating a subset of parameters for each token, MoE architecture could increase…

Text response generation for multimodal task-oriented dialog systems, which aims to generate the proper text response given the multimodal context, is an essential yet challenging task. Although existing efforts have achieved compelling…

Emotional Text-to-Speech (E-TTS) synthesis has garnered significant attention in recent years due to its potential to revolutionize human-computer interaction. However, current E-TTS approaches often struggle to capture the intricacies of…

Contemporary transformer architectures apply identical processing depth to all inputs, creating inefficiencies and limiting reasoning quality. Simple factual queries are subjected to the same multilayered computation as complex logical…

Previous research on empathetic dialogue systems has mostly focused on generating responses given certain emotions. However, being empathetic not only requires the ability of generating emotional responses, but more importantly, requires…

Current task-oriented dialog (TOD) systems mostly manage structured knowledge (e.g. databases and tables) to guide the goal-oriented conversations. However, they fall short of handling dialogs which also involve unstructured knowledge (e.g.…

Despite recent advancements in offline multi-task reinforcement learning (MTRL) have harnessed the powerful capabilities of the Transformer architecture, most approaches focus on a limited number of tasks, with scaling to extremely massive…

In recent years, neural network based methods for multi-speaker text-to-speech synthesis (TTS) have made significant progress. However, the current speaker encoder models used in these methods still cannot capture enough speaker…

Previous dialogue summarization datasets mainly focus on open-domain chitchat dialogues, while summarization datasets for the broadly used task-oriented dialogue haven't been explored yet. Automatically summarizing such task-oriented…

When applied directly in an end-to-end manner to medical follow-up tasks, Large Language Models (LLMs) often suffer from uncontrolled dialog flow and inaccurate information extraction due to the complexity of follow-up forms. To address…