Pre-trained models have proved to be powerful in enhancing task-oriented dialog systems.
However, current pre-training methods mainly focus on enhancing dialog understanding …

Recently, pre-training methods have shown remarkable success in task-oriented dialog
(TOD) systems. However, most existing pre-trained models for TOD focus on either dialog …

Pre-training methods with contrastive learning objectives have shown remarkable success
in dialog understanding tasks. However, current contrastive learning solely considers the …

The future of conversational agents will provide users with personalized information
responses. However, a significant challenge in developing models is the lack of large-scale …

In this paper, we introduce the task of learning unsupervised dialogue embeddings. Trivial
approaches such as combining pre-trained word or sentence embeddings and encoding …

Recently, pre-training methods have shown remarkable success in task-oriented dialog
(TOD) systems. However, most existing pre-trained models for TOD focus on either dialog …

Despite the recent advances in coherence modelling, most such models including state-of-
the-art neural ones, are evaluated on either contrived proxy tasks such as the standard order …

Creating conversational dialog systems that are able to converse naturally and engagingly
with humans on any topic remains one of the fundamental challenges of artificial …

Discourse relation identification has been an active area of research for many years, and the
challenge of identifying implicit relations remains largely an unsolved task, especially in the …

Large pre-trained language generation models such as GPT-2 have demonstrated their
effectiveness as language priors by reaching state-of-the-art results in various language …