Related papers: Learning End-to-End Goal-Oriented Dialog with Mult…

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…

End-to-end multi-task dialogue systems are usually designed with separate modules for the dialogue pipeline. Among these, the policy module is essential for deciding what to do in response to user input. This policy is trained by…

Learning a goal-oriented dialog policy is generally performed offline with supervised learning algorithms or online with reinforcement learning (RL). Additionally, as companies accumulate massive quantities of dialog transcripts between…

We propose a novel methodology to address dialog learning in the context of goal-oriented conversational systems. The key idea is to quantize the dialog space into clusters and create a language model across the clusters, thus allowing for…

The goal-oriented document-grounded dialogue aims at responding to the user query based on the dialogue context and supporting document. Existing studies tackle this problem by decomposing it into two sub-tasks: knowledge identification and…

A long-term goal of machine learning research is to build an intelligent dialog agent. Most research in natural language understanding has focused on learning from fixed training sets of labeled data, with supervision either at the word…

Natural language understanding and dialogue policy learning are both essential in conversational systems that predict the next system actions in response to a current user utterance. Conventional approaches aggregate separate models of…

Machine-learning based dialogue managers are able to learn complex behaviors in order to complete a task, but it is not straightforward to extend their capabilities to new domains. We investigate different policies' ability to handle…

Task-oriented dialogue (ToD) benchmarks provide an important avenue to measure progress and develop better conversational agents. However, existing datasets for end-to-end ToD modeling are limited to a single language, hindering the…

Automatic dialogue evaluation plays a crucial role in open-domain dialogue research. Previous works train neural networks with limited annotation for conducting automatic dialogue evaluation, which would naturally affect the evaluation…

Most dialog systems posit that users have figured out clear and specific goals before starting an interaction. For example, users have determined the departure, the destination, and the travel time for booking a flight. However, in many…

Linguistic entrainment, or alignment, represents a phenomenon where linguistic patterns employed by conversational participants converge to one another. While entrainment has been shown to produce a more natural user experience, most…

Tuning language models for dialogue generation has been a prevalent paradigm for building capable dialogue agents. Yet, traditional tuning narrowly views dialogue generation as resembling other language generation tasks, ignoring the role…

End-to-end neural models for intelligent dialogue systems suffer from the problem of generating uninformative responses. Various methods were proposed to generate more informative responses by leveraging external knowledge. However, few…

This work investigates the task-oriented dialogue problem in mixed-domain settings. We study the effect of alternating between different domains in sequences of dialogue turns using two related state-of-the-art dialogue systems. We first…

Dialog policy decides what and how a task-oriented dialog system will respond, and plays a vital role in delivering effective conversations. Many studies apply Reinforcement Learning to learn a dialog policy with the reward function which…

Task-oriented Dialog (ToD) systems have to solve multiple subgoals to accomplish user goals, whereas feedback is often obtained only at the end of the dialog. In this work, we propose SUIT (SUbgoal-aware ITerative Training), an iterative…

A limitation of current neural dialog models is that they tend to suffer from a lack of specificity and informativeness in generated responses, primarily due to dependence on training data that covers a limited variety of scenarios and…

End-to-end learning framework is useful for building dialog systems for its simplicity in training and efficiency in model updating. However, current end-to-end approaches only consider user semantic inputs in learning and under-utilize…

Building an end-to-end conversational agent for multi-domain task-oriented dialogues has been an open challenge for two main reasons. First, tracking dialogue states of multiple domains is non-trivial as the dialogue agent must obtain…