Related papers: DiactTOD: Learning Generalizable Latent Dialogue A…

Popular dialog datasets such as MultiWOZ are created by providing crowd workers an instruction, expressed in natural language, that describes the task to be accomplished. Crowd workers play the role of a user and an agent to generate…

Zero-shot dialogue understanding aims to enable dialogue to track the user's needs without any training data, which has gained increasing attention. In this work, we investigate the understanding ability of ChatGPT for zero-shot dialogue…

Mixed-initiative dialogue tasks involve repeated exchanges of information and conversational control. Conversational agents gain control by generating responses that follow particular dialogue intents or strategies, prescribed by a policy…

While end-to-end neural conversation models have led to promising advances in reducing hand-crafted features and errors induced by the traditional complex system architecture, they typically require an enormous amount of data due to the…

Traditional end-to-end task-oriented dialogue systems have been built with a modularized design. However, such design often causes misalignment between the agent response and external knowledge, due to inadequate representation of…

The adoption of pre-trained language models in task-oriented dialogue systems has resulted in significant enhancements of their text generation abilities. However, these architectures are slow to use because of the large number of trainable…

When a natural language generation (NLG) component is implemented in a real-world task-oriented dialogue system, it is necessary to generate not only natural utterances as learned on training data but also utterances adapted to the dialogue…

Dialogue act recognition is an important part of natural language understanding. We investigate the way dialogue act corpora are annotated and the learning approaches used so far. We find that the dialogue act is context-sensitive within…

Goal-oriented dialog systems enable users to complete specific goals like requesting information about a movie or booking a ticket. Typically the dialog system pipeline contains multiple ML models, including natural language understanding,…

The recent development of language models has shown promising results by achieving state-of-the-art performance on various natural language tasks by fine-tuning pretrained models. In task-oriented dialogue (ToD) systems, language models can…

Pre-trained conversation models (PCMs) have achieved promising progress in recent years. However, existing PCMs for Task-oriented dialog (TOD) are insufficient for capturing the sequential nature of the TOD-related tasks, as well as for…

Task-oriented dialog presents a difficult challenge encompassing multiple problems including multi-turn language understanding and generation, knowledge retrieval and reasoning, and action prediction. Modern dialog systems typically begin…

Imitation learning is effective for training agents when expert demonstrations are available, but collecting demonstrations for every complex task in an environment is costly. We study the long-horizon, goal-conditioned setting where a…

Goal-oriented dialogue systems face a trade-off between fluent language generation and task-specific control. While supervised learning with large language models is capable of producing realistic text, how to steer such responses towards…

Dialogue systems are usually categorized into two types, open-domain and task-oriented. The first one focuses on chatting with users and making them engage in the conversations, where selecting a proper topic to fit the dialogue context is…

Existing dialog system models require extensive human annotations and are difficult to generalize to different tasks. The recent success of large pre-trained language models such as BERT and GPT-2 (Devlin et al., 2019; Radford et al., 2019)…

Dialogue State Tracking (DST) is designed to monitor the evolving dialogue state in the conversations and plays a pivotal role in developing task-oriented dialogue systems. However, obtaining the annotated data for the DST task is usually a…

Collecting and annotating task-oriented dialogues is time-consuming and costly; thus, zero and few shot learning could greatly benefit dialogue state tracking (DST). In this work, we propose an in-context learning (ICL) framework for…

Domain adaptation has recently become a key problem in dialogue systems research. Deep learning, while being the preferred technique for modeling such systems, works best given massive training data. However, in the real-world scenario,…

This paper studies the exposure bias problem in task-oriented dialog systems, where the model's generated content over multiple turns drives the dialog context away from the ground-truth distribution at training time, introducing error…