Related papers: Multi-level Memory for Task Oriented Dialogs

Existing studies in dialogue system research mostly treat task-oriented dialogue and chit-chat as separate domains. Towards building a human-like assistant that can converse naturally and seamlessly with users, it is important to build a…

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…

Pre-trained language models (PLM) have advanced the state-of-the-art across NLP applications, but lack domain-specific knowledge that does not naturally occur in pre-training data. Previous studies augmented PLMs with symbolic knowledge for…

Recent work has shown that attention-based language models excel at recall, the ability to ground generations in tokens previously seen in context. However, the efficiency of attention-based models is bottle-necked during inference by the…

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…

Constructing responses in task-oriented dialogue systems typically relies on information sources such the current dialogue state or external databases. This paper presents a novel approach to knowledge-grounded response generation that…

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…

To alleviate the problem of structured databases' limited coverage, recent task-oriented dialogue systems incorporate external unstructured knowledge to guide the generation of system responses. However, these usually use word or sentence…

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…

Transfer learning is an exciting area of Natural Language Processing that has the potential to both improve model performance and increase data efficiency. This study explores the effects of varying quantities of target task training data…

This paper proposes KB-InfoBot -- a multi-turn dialogue agent which helps users search Knowledge Bases (KBs) without composing complicated queries. Such goal-oriented dialogue agents typically need to interact with an external database to…

Existing pipelined task-oriented dialogue systems usually have difficulties adapting to unseen domains, whereas end-to-end systems are plagued by large-scale knowledge bases in practice. In this paper, we introduce a novel query-driven…

Dialog systems have achieved significant progress and have been widely used in various scenarios. The previous researches mainly focused on designing dialog generation models in a single scenario, while comprehensive abilities are required…

Long-term memory is important for chatbots and dialogue systems (DS) to create consistent and human-like conversations, evidenced by numerous developed memory-augmented DS (MADS). To evaluate the effectiveness of such MADS, existing…

Task-oriented dialogue systems have been plagued by the difficulties of obtaining large-scale and high-quality annotated conversations. Furthermore, most of the publicly available datasets only include written conversations, which are…

Knowledge graph-based dialogue systems can narrow down knowledge candidates for generating informative and diverse responses with the use of prior information, e.g., triple attributes or graph paths. However, most current knowledge graph…

In open-domain conversational systems, it is important but challenging to leverage background knowledge. We can use the incorporation of knowledge to make the generation of dialogue controllable, and can generate more diverse sentences that…

Multi-party dialogue machine reading comprehension (MRC) raises an even more challenging understanding goal on dialogue with more than two involved speakers, compared with the traditional plain passage style MRC. To accurately perform the…

End-to-End intelligent neural dialogue systems suffer from the problems of generating inconsistent and repetitive responses. Existing dialogue models pay attention to unilaterally incorporating personal knowledge into the dialog while…

We describe a two-step approach for dialogue management in task-oriented spoken dialogue systems. A unified neural network framework is proposed to enable the system to first learn by supervision from a set of dialogue data and then…