Related papers: Efficient Task-Oriented Dialogue Systems with Resp…
Data scarcity is a long-standing and crucial challenge that hinders quick development of task-oriented dialogue systems across multiple domains: task-oriented dialogue models are expected to learn grammar, syntax, dialogue reasoning,…
Attention-based pre-trained language models such as GPT-2 brought considerable progress to end-to-end dialogue modelling. However, they also present considerable risks for task-oriented dialogue, such as lack of knowledge grounding or…
Collection of annotated dialogs for training task-oriented dialog systems have been one of the key bottlenecks in improving current models. While dialog response generation has been widely studied on the agent side, it is not evident if…
Data artifacts incentivize machine learning models to learn non-transferable generalizations by taking advantage of shortcuts in the data, and there is growing evidence that data artifacts play a role for the strong results that deep…
This work combines information about the dialogue history encoded by pre-trained model with a meaning representation of the current system utterance to realize contextual language generation in task-oriented dialogues. We utilize 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…
Most prior work on task-oriented dialogue systems are restricted to a limited coverage of domain APIs, while users oftentimes have domain related requests that are not covered by the APIs. In this paper, we propose to expand coverage of…
Task-oriented dialog systems have witnessed substantial progress due to conversational pre-training techniques. Yet, two significant challenges persist. First, most systems primarily utilize the latest turn's state label for the generator.…
Task-oriented dialogue is often decomposed into three tasks: understanding user input, deciding actions, and generating a response. While such decomposition might suggest a dedicated model for each sub-task, we find a simple, unified…
While most task-oriented dialogues assume conversations between the agent and one user at a time, dialogue systems are increasingly expected to communicate with multiple users simultaneously who make decisions collaboratively. To facilitate…
Autoregressive models used to generate responses in open-domain dialogue systems often struggle to take long-term context into account and to maintain consistency over a dialogue. Previous research in open-domain dialogue generation has…
Dialogue policy learning, a subtask that determines the content of system response generation and then the degree of task completion, is essential for task-oriented dialogue systems. However, the unbalanced distribution of system actions in…
We study multi-turn response generation for open-domain dialogues. The existing state-of-the-art addresses the problem with deep neural architectures. While these models improved response quality, their complexity also hinders the…
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…
In this paper, we propose to formulate the task-oriented dialogue system as the purely natural language generation task, so as to fully leverage the large-scale pre-trained models like GPT-2 and simplify complicated delexicalization…
Despite their popularity in the chatbot literature, retrieval-based models have had modest impact on task-oriented dialogue systems, with the main obstacle to their application being the low-data regime of most task-oriented dialogue tasks.…
Efficient knowledge retrieval plays a pivotal role in ensuring the success of end-to-end task-oriented dialogue systems by facilitating the selection of relevant information necessary to fulfill user requests. However, current approaches…
Task-Oriented Dialogue (TOD) systems are drawing more and more attention in recent studies. Current methods focus on constructing pre-trained models or fine-tuning strategies while the evaluation of TOD is limited by a policy mismatch…
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…
Task-oriented conversational systems often use dialogue state tracking to represent the user's intentions, which involves filling in values of pre-defined slots. Many approaches have been proposed, often using task-specific architectures…