相关论文: Hybrid Generative-Retrieval Transformers for Dialo…

Current generative-based dialogue systems are data-hungry and fail to adapt to new unseen domains when only a small amount of target data is available. Additionally, in real-world applications, most domains are underrepresented, so there is…

This paper describes our submission for the End-to-end Multi-domain Task Completion Dialog shared task at the 9th Dialog System Technology Challenge (DSTC-9). Participants in the shared task build an end-to-end task completion dialog system…

Dialogue State Tracking is central to multi-domain task-oriented dialogue systems, responsible for extracting information from user utterances. We present a novel hybrid architecture that augments GPT-2 with representations derived from…

Despite the tremendous success of neural dialogue models in recent years, it suffers a lack of relevance, diversity, and some times coherence in generated responses. Lately, transformer-based models, such as GPT-2, have revolutionized the…

Domain adaptation is an essential task in dialog system building because there are so many new dialog tasks created for different needs every day. Collecting and annotating training data for these new tasks is costly since it involves real…

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 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,…

Goal-oriented dialogue systems are now being widely adopted in industry where it is of key importance to maintain a rapid prototyping cycle for new products and domains. Data-driven dialogue system development has to be adapted to meet this…

Most research on dialogue has focused either on dialogue generation for openended chit chat or on state tracking for goal-directed dialogue. In this work, we explore a hybrid approach to goal-oriented dialogue generation that combines…

Numerous new dialog domains are being created every day while collecting data for these domains is extremely costly since it involves human interactions. Therefore, it is essential to develop algorithms that can adapt to different domains…

The remarkable success of large language models has been driven by dense models trained on massive unlabeled, unstructured corpora. These corpora typically contain text from diverse, heterogeneous sources, but information about the source…

Building systems that can communicate with humans is a core problem in Artificial Intelligence. This work proposes a novel neural network architecture for response selection in an end-to-end multi-turn conversational dialogue setting. The…

Retrieval-Augmented Generation (RAG) has emerged as a powerful approach for enhancing large language models' question-answering capabilities through the integration of external knowledge. However, when adapting RAG systems to specialized…

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…

Learning with minimal data is one of the key challenges in the development of practical, production-ready goal-oriented dialogue systems. In a real-world enterprise setting where dialogue systems are developed rapidly and are expected to…

One of the difficulties in training dialogue systems is the lack of training data. We explore the possibility of creating dialogue data through the interaction between a dialogue system and a user simulator. Our goal is to develop a…

Dialog policy determines the next-step actions for agents and hence is central to a dialogue system. However, when migrated to novel domains with little data, a policy model can fail to adapt due to insufficient interactions with the new…

Recently, utilizing deep neural networks to build the opendomain dialogue models has become a hot topic. However, the responses generated by these models suffer from many problems such as responses not being contextualized and tend to…

Current state-of-the-art dialogue systems heavily rely on extensive training datasets. However, challenges arise in domains where domain-specific training datasets are insufficient or entirely absent. To tackle this challenge, we propose a…

This paper describes our approach to DSTC 9 Track 2: Cross-lingual Multi-domain Dialog State Tracking, the task goal is to build a Cross-lingual dialog state tracker with a training set in rich resource language and a testing set in low…