Related papers: Resource Constrained Dialog Policy Learning via Di…

Task oriented dialogue systems rely heavily on specialized dialogue state tracking (DST) modules for dynamically predicting user intent throughout the conversation. State-of-the-art DST models are typically trained in a supervised manner…

Dialogue state tracking (DST) is a crucial module in dialogue management. It is usually cast as a supervised training problem, which is not convenient for on-line optimization. In this paper, a novel companion teaching based deep…

Reinforcement learning (RL) has demonstrated great success in the past several years. However, most of the scenarios focus on simulated environments. One of the main challenges of transferring the policy learned in a simulated environment…

Continuous-action policies trained on a single demonstrated trajectory per scene suffer from mode collapse: samples cluster around the demonstrated maneuver and the policy cannot represent semantically distinct alternatives. Under…

Conversational Tree Search (V\"ath et al., 2023) is a recent approach to controllable dialog systems, where domain experts shape the behavior of a Reinforcement Learning agent through a dialog tree. The agent learns to efficiently navigate…

Recent studies have shown remarkable success in end-to-end task-oriented dialog system. However, most neural models rely on large training data, which are only available for a certain number of task domains, such as navigation and…

Zero-shot transfer learning for Dialogue State Tracking (DST) helps to handle a variety of task-oriented dialogue domains without the cost of collecting in-domain data. Existing works mainly study common data- or model-level augmentation…

Domain adaptation is an essential task in dialog system building because there are so many new dialog tasks created for different needs every day. Collecting and annotating training data for these new tasks is costly since it involves real…

The recent advent of neural approaches for developing each dialog component in task-oriented dialog systems has remarkably improved, yet optimizing the overall system performance remains a challenge. Besides, previous research on modeling…

This paper introduces zero-shot dialog generation (ZSDG), as a step towards neural dialog systems that can instantly generalize to new situations with minimal data. ZSDG enables an end-to-end generative dialog system to generalize to a new…

Zero-shot domain adaptation for dialogue state tracking (DST) remains a challenging problem in task-oriented dialogue (TOD) systems, where models must generalize to target domains unseen at training time. Current large language model…

Large language models (LLMs), optimized through human feedback, have rapidly emerged as a leading paradigm for developing intelligent conversational assistants. However, despite their strong performance across many benchmarks, LLM-based…

This paper is concerned with the training of recurrent neural networks as goal-oriented dialog agents using reinforcement learning. Training such agents with policy gradients typically requires a large amount of samples. However, the…

Zero-shot cross-lingual transfer is promising, however has been shown to be sub-optimal, with inferior transfer performance across low-resource languages. In this work, we envision languages as domains for improving zero-shot transfer by…

Few-shot dialogue state tracking (DST) is a realistic problem that trains the DST model with limited labeled data. Existing few-shot methods mainly transfer knowledge learned from external labeled dialogue data (e.g., from question…

We demonstrate task-oriented dialogue generation within the dataflow dialogue paradigm. We show an example of agenda driven dialogue generation for the MultiWOZ domain, and an example of generation without an agenda for the SMCalFlow…

In this paper, we present a neural network based task-oriented dialogue system that can be optimized end-to-end with deep reinforcement learning (RL). The system is able to track dialogue state, interface with knowledge bases, and…

Open domain dialog systems face the challenge of being repetitive and producing generic responses. In this paper, we demonstrate that by conditioning the response generation on interpretable discrete dialog attributes and composed…

While multi-party conversations are often less structured than monologues and documents, they are implicitly organized by semantic level correlations across the interactive turns, and dialogue discourse analysis can be applied to predict…

Data-driven systems depend on task-relevant data, yet data collection pipelines remain passive and indiscriminate. Continuous logging of multimodal sensor streams incurs high storage costs and captures irrelevant data. This paper proposes a…