Related papers: Efficient Context and Schema Fusion Networks for M…
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…
We demonstrate substantial performance gains in zero-shot dialogue state tracking (DST) by enhancing training data diversity through synthetic data generation. Existing DST datasets are severely limited in the number of application domains…
Dialogue state tracking (DST) aims to convert the dialogue history into dialogue states which consist of slot-value pairs. As condensed structural information memorizing all history information, the dialogue state in the last turn is…
Dialogue state tracking (DST) is an essential component in task-oriented dialogue systems, which estimates user goals at every dialogue turn. However, most previous approaches usually suffer from the following problems. Many discriminative…
Recent studies have shown remarkable success in end-to-end task-oriented dialog system. However, most neural models rely on large training data, which are only available for a certain number of task domains, such as navigation and…
This paper presents our novel method to encode word confusion networks, which can represent a rich hypothesis space of automatic speech recognition systems, via recurrent neural networks. We demonstrate the utility of our approach for the…
This paper proposes an improvement to the existing data-driven Neural Belief Tracking (NBT) framework for Dialogue State Tracking (DST). The existing NBT model uses a hand-crafted belief state update mechanism which involves an expensive…
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…
Recently, research on open domain dialogue systems have attracted extensive interests of academic and industrial researchers. The goal of an open domain dialogue system is to imitate humans in conversations. Previous works on single turn…
Dialogue State Tracking (DST) models often employ intricate neural network architectures, necessitating substantial training data, and their inference process lacks transparency. This paper proposes a method that extracts linguistic…
Semantic parsing has long been a fundamental problem in natural language processing. Recently, cross-domain context-dependent semantic parsing has become a new focus of research. Central to the problem is the challenge of leveraging…
Establishing semantic correspondence is a core problem in computer vision and remains challenging due to large intra-class variations and lack of annotated data. In this paper, we aim to incorporate global semantic context in a flexible…
A Dialogue State Tracker is a key component in dialogue systems which estimates the beliefs of possible user goals at each dialogue turn. Deep learning approaches using recurrent neural networks have shown state-of-the-art performance for…
Robust state tracking for task-oriented dialogue systems currently remains restricted to a few popular languages. This paper shows that given a large-scale dialogue data set in one language, we can automatically produce an effective…
Automated negotiation support systems aim to help human negotiators reach more favorable outcomes in multi-issue negotiations (e.g., an employer and a candidate negotiating over issues such as salary, hours, and promotions before a job…
This paper gives an overview of the Schema-Guided Dialogue State Tracking task of the 8th Dialogue System Technology Challenge. The goal of this task is to develop dialogue state tracking models suitable for large-scale virtual assistants,…
Previous zero-shot dialogue state tracking (DST) methods only apply transfer learning, ignoring unlabelled data in the target domain. We transform zero-shot DST into few-shot DST by utilising such unlabelled data via joint and self-training…
Data augmentation methods have been a promising direction to improve the performance of small models for low-resource dialogue state tracking. However, traditional methods rely on pre-defined user goals and neglect the importance of data…
An indispensable component in task-oriented dialogue systems is the dialogue state tracker, which keeps track of users' intentions in the course of conversation. The typical approach towards this goal is to fill in multiple pre-defined…
Neural dialog models have exhibited strong performance, however their end-to-end nature lacks a representation of the explicit structure of dialog. This results in a loss of generalizability, controllability and a data-hungry nature.…