Related papers: An End-to-End Trainable Neural Network Model with …

End-to-end Task-oriented Dialogue Systems (TDSs) have attracted a lot of attention for their superiority (e.g., in terms of global optimization) over pipeline modularized TDSs. Previous studies on end-to-end TDSs use a single-module model…

Spoken language understanding, which extracts intents and/or semantic concepts in utterances, is conventionally formulated as a post-processing of automatic speech recognition. It is usually trained with oracle transcripts, but needs to…

Dialogue data in real scenarios tend to be sparsely available, rendering data-starved end-to-end dialogue systems trained inadequately. We discover that data utilization efficiency in low-resource scenarios can be enhanced by mining…

Augmentation of task-oriented dialogues has followed standard methods used for plain-text such as back-translation, word-level manipulation, and paraphrasing despite its richly annotated structure. In this work, we introduce an augmentation…

This paper presents results from the first attempt to apply Transformation-Based Learning to a discourse-level Natural Language Processing task. To address two limitations of the standard algorithm, we developed a Monte Carlo version of…

Attention-based pre-trained language models such as GPT-2 brought considerable progress to end-to-end dialogue modelling. However, they also present considerable risks for task-oriented dialogue, such as lack of knowledge grounding or…

We describe a system for building task-oriented dialogue systems combining the in-context learning abilities of large language models (LLMs) with the deterministic execution of business logic. LLMs are used to translate between the surface…

This work proposes a novel approach based on sequence-to-sequence (seq2seq) models for context-aware conversational systems. Exist- ing seq2seq models have been shown to be good for generating natural responses in a data-driven…

Programmable task-oriented dialogue (TOD) agents enable language models to follow structured dialogue policies, but their effectiveness hinges on accurate state tracking. We present PyTOD, an agent that generates executable code to track…

We introduce provenance networks, a novel class of neural models designed to provide end-to-end, training-data-driven explainability. Unlike conventional post-hoc methods, provenance networks learn to link each prediction directly to its…

The End-to-end (E2E) learning-based approach has great potential to reshape the existing communication systems by replacing the transceivers with deep neural networks. To this end, the E2E learning approach needs to assume the availability…

In task-oriented dialogs (TOD), reinforcement learning (RL) algorithms train a model to directly optimize response for task-related metrics. However, RL needs to perform exploration, which can be time-consuming due to the slow…

Intent detection is a key part of any Natural Language Understanding (NLU) system of a conversational assistant. Detecting the correct intent is essential yet difficult for email conversations where multiple directives and intents are…

The training of task-oriented dialogue systems is often confronted with the lack of annotated data. In contrast to previous work which augments training data through expensive crowd-sourcing efforts, we propose four different automatic…

We present our work on Track 2 in the Dialog System Technology Challenges 7 (DSTC7). The DSTC7-Track 2 aims to evaluate the response generation of fully data-driven conversation models in knowledge-grounded settings, which provides the…

Task-oriented dialog (TOD) systems typically manage structured knowledge (e.g. ontologies and databases) to guide the goal-oriented conversations. However, they fall short of handling dialog turns grounded on unstructured knowledge (e.g.…

Deep learning models are often deployed in downstream tasks that the training procedure may not be aware of. For example, models solely trained to achieve accurate predictions may struggle to perform well on downstream tasks because…

We demonstrate that large language models are able to simulate Task Oriented Dialogues in novel domains, provided only with an API implementation and a list of goals. We show these simulations can formulate online, automatic metrics that…

Dialogue state tracking is an important component in task-oriented dialogue systems to identify users' goals and requests as a dialogue proceeds. However, as most previous models are dependent on dialogue slots, the model complexity soars…

During the past decade, several areas of speech and language understanding have witnessed substantial breakthroughs from the use of data-driven models. In the area of dialogue systems, the trend is less obvious, and most practical systems…