Related papers: DiactTOD: Learning Generalizable Latent Dialogue A…
We demonstrate substantial performance gains in zero-shot dialogue state tracking (DST) by enhancing training data diversity through synthetic data generation. Existing DST datasets are severely limited in the number of application domains…
Based on the recently proposed transferable dialogue state generator (TRADE) that predicts dialogue states from utterance-concatenated dialogue context, we propose a multi-task learning model with a simple yet effective utterance tagging…
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…
Dialogue policy optimization often obtains feedback until task completion in task-oriented dialogue systems. This is insufficient for training intermediate dialogue turns since supervision signals (or rewards) are only provided at the end…
End-to-end task-oriented dialogue (TOD) systems have achieved promising performance by leveraging sophisticated natural language understanding and natural language generation capabilities of pre-trained models. This work enables the TOD…
Annotating task-oriented dialogues is notorious for the expensive and difficult data collection process. Few-shot dialogue state tracking (DST) is a realistic solution to this problem. In this paper, we hypothesize that dialogue summaries…
Previous zero-shot dialogue state tracking (DST) methods only apply transfer learning, ignoring unlabelled data in the target domain. We transform zero-shot DST into few-shot DST by utilising such unlabelled data via joint and self-training…
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…
End-to-end task-oriented dialogue (EToD) can directly generate responses in an end-to-end fashion without modular training, which attracts escalating popularity. The advancement of deep neural networks, especially the successful use of…
We present an approach called Dialogue Action Tokens (DAT) that adapts language model agents to plan goal-directed dialogues. The core idea is to treat each utterance as an action, thereby converting dialogues into games where existing…
Dialog act prediction is an essential language comprehension task for both dialog system building and discourse analysis. Previous dialog act schemes, such as SWBD-DAMSL, are designed for human-human conversations, in which conversation…
We describe an approach to task-oriented dialogue in which dialogue state is represented as a dataflow graph. A dialogue agent maps each user utterance to a program that extends this graph. Programs include metacomputation operators for…
Target-Oriented Dialogue (TOD) remains a significant challenge in the LLM era, where strategic dialogue planning is crucial for directing conversations toward specific targets. However, existing dialogue planning methods generate dialogue…
We present a novel architecture for explainable modeling of task-oriented dialogues with discrete latent variables to represent dialogue actions. Our model is based on variational recurrent neural networks (VRNN) and requires no explicit…
Dialogue State Tracking (DST), a key component of task-oriented conversation systems, represents user intentions by determining the values of pre-defined slots in an ongoing dialogue. Existing approaches use hand-crafted templates and…
A significant application of Large Language Models (LLMs), like ChatGPT, is their deployment as chat agents, which respond to human inquiries across a variety of domains. While current LLMs proficiently answer general questions, they often…
Task-oriented dialogue focuses on conversational agents that participate in user-initiated dialogues on domain-specific topics. In contrast to chatbots, which simply seek to sustain open-ended meaningful discourse, existing task-oriented…
Utilizing amortized variational inference for latent-action reinforcement learning (RL) has been shown to be an effective approach in Task-oriented Dialogue (ToD) systems for optimizing dialogue success. Until now, categorical posteriors…
Recent advances in task-oriented dialogue (TOD) systems, driven by large language models (LLMs) with extensive API and tool integration, have enabled conversational agents to coordinate interleaved goals, maintain long-horizon context, and…
End-to-end neural approaches are becoming increasingly common in conversational scenarios due to their promising performances when provided with sufficient amount of data. In this paper, we present a novel methodology to address the…