Related papers: Toward Scalable Neural Dialogue State Tracking Mod…

Natural language generation plays a critical role in spoken dialogue systems. We present a new approach to natural language generation for task-oriented dialogue using recurrent neural networks in an encoder-decoder framework. In contrast…

Dialog state tracking is a key component of many modern dialog systems, most of which are designed with a single, well-defined domain in mind. This paper shows that dialog data drawn from different dialog domains can be used to train a…

Mainstream cross-lingual task-oriented dialogue (ToD) systems leverage the transfer learning paradigm by training a joint model for intent recognition and slot-filling in English and applying it, zero-shot, to other languages. We address a…

Task-oriented dialogue (TOD) systems enable users to achieve their goals through natural language interactions. Traditionally, these systems have relied on turn-level manually annotated metadata, such as dialogue states and policy…

With the availability of massive general-domain dialogue data, pre-trained dialogue generation appears to be super appealing to transfer knowledge from the general domain to downstream applications. In most existing work, such transferable…

Multi-intent SLU can handle multiple intents in an utterance, which has attracted increasing attention. However, the state-of-the-art joint models heavily rely on autoregressive approaches, resulting in two issues: slow inference speed and…

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…

Dialogue state tracking (DST) is at the heart of task-oriented dialogue systems. However, the scarcity of labeled data is an obstacle to building accurate and robust state tracking systems that work across a variety of domains. Existing…

Inspired by recent work in meta-learning and generative teaching networks, we propose a framework called Generative Conversational Networks, in which conversational agents learn to generate their own labelled training data (given some seed…

Spoken language understanding (SLU) acts as a critical component in goal-oriented dialog systems. It typically involves identifying the speakers intent and extracting semantic slots from user utterances, which are known as intent detection…

The pre-dominant approach to language modeling to date is based on recurrent neural networks. Their success on this task is often linked to their ability to capture unbounded context. In this paper we develop a finite context approach…

In task-oriented dialogue systems, Dialogue State Tracking (DST) aims to extract users' intentions from the dialogue history. Currently, most existing approaches suffer from error propagation and are unable to dynamically select relevant…

Goal-oriented dialogue systems face a trade-off between fluent language generation and task-specific control. While supervised learning with large language models is capable of producing realistic text, how to steer such responses towards…

Dialogue state tracking (DST) aims at estimating the current dialogue state given all the preceding conversation. For multi-domain DST, the data sparsity problem is a major obstacle due to increased numbers of state candidates and dialogue…

Stochastic distributed optimization methods that solve an optimization problem over a multi-agent network have played an important role in a variety of large-scale signal processing and machine leaning applications. Among the existing…

Existing template and learning-based APR tools have successfully found patches for many benchmark faults. However, our analysis of existing results shows that omission faults pose a significant challenge to these techniques. For template…

Dialogue state tracking (DST) is an essential sub-task for task-oriented dialogue systems. Recent work has focused on deep neural models for DST. However, the neural models require a large dataset for training. Furthermore, applying them to…

Transformer models have become foundational across a wide range of scientific and engineering domains due to their strong empirical performance. A key capability underlying their success is in-context learning (ICL): when presented with a…

Task-oriented dialogue systems -- handling transactions, reservations, and service requests -- require predictable behavior, yet the moderately-sized LLMs needed for practical latency are prone to hallucination and format errors that…

This paper presents a novel framework for Speech Activity Detection (SAD). Inspired by the recent success of multi-task learning approaches in the speech processing domain, we propose a novel joint learning framework for SAD. We utilise…