Related papers: End-to-End Task-Oriented Dialog Modeling with Semi…
In real-world task-oriented dialogue (TOD) settings, agents are required to strictly adhere to complex instructions while conducting multi-turn conversations with customers. These instructions are typically presented in natural language…
The design of dialogue flows is a critical but time-consuming task when developing task-oriented dialogue (TOD) systems. We propose an approach for the unsupervised discovery of flows from dialogue history, thus making the process…
In light of recent advances in large language models (LLMs), the expectations for the next generation of virtual assistants include enhanced naturalness and adaptability across diverse usage scenarios. However, the creation of high-quality…
Deploying accurate Text-to-SQL systems at the enterprise level faces a difficult trilemma involving cost, security and performance. Current solutions force enterprises to choose between expensive, proprietary Large Language Models (LLMs)…
Task-oriented dialogue (TOD) systems have been widely deployed in many industries as they deliver more efficient customer support. These systems are typically constructed for a single domain or language and do not generalise well beyond…
This paper presents a model for end-to-end learning of task-oriented dialog systems. The main component of the model is a recurrent neural network (an LSTM), which maps from raw dialog history directly to a distribution over system actions.…
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…
An important open question in the use of large language models for knowledge-intensive tasks is how to effectively integrate knowledge from three sources: the model's parametric memory, external structured knowledge, and external…
Goal-oriented dialog systems, which can be trained end-to-end without manually encoding domain-specific features, show tremendous promise in the customer support use-case e.g. flight booking, hotel reservation, technical support, student…
Semi-Supervised Semantic Segmentation reduces reliance on extensive annotations by using unlabeled data and state-of-the-art models to improve overall performance. Despite the success of deep co-training methods, their underlying mechanisms…
End-to-end architectures have been recently proposed for spoken language understanding (SLU) and semantic parsing. Based on a large amount of data, those models learn jointly acoustic and linguistic-sequential features. Such architectures…
Structured belief states are crucial for user goal tracking and database query in task-oriented dialog systems. However, training belief trackers often requires expensive turn-level annotations of every user utterance. In this paper we aim…
Traditional dialog systems used in goal-oriented applications require a lot of domain-specific handcrafting, which hinders scaling up to new domains. End-to-end dialog systems, in which all components are trained from the dialogs…
Task-oriented dialogue (ToD) systems have been mostly created for high-resource languages, such as English and Chinese. However, there is a need to develop ToD systems for other regional or local languages to broaden their ability to…
Dialogue policy optimization often obtains feedback until task completion in task-oriented dialogue systems. This is insufficient for training intermediate dialogue turns since supervision signals (or rewards) are only provided at the end…
Pre-trained language models based on general text enable huge success in the NLP scenario. But the intrinsical difference of linguistic patterns between general text and task-oriented dialogues makes existing pre-trained language models…
Building end-to-end task bots and maintaining their integration with new functionalities using minimal human efforts is a long-standing challenge in dialog research. Recently large language models (LLMs) have demonstrated exceptional…
Learning an efficient manager of dialogue agent from data with little manual intervention is important, especially for goal-oriented dialogues. However, existing methods either take too many manual efforts (e.g. reinforcement learning…
Neural network models are capable of generating extremely natural sounding conversational interactions. Nevertheless, these models have yet to demonstrate that they can incorporate content in the form of factual information or…
Task-oriented dialogue (TOD) systems aim to achieve specific goals through interactive dialogue. Such tasks usually involve following specific workflows, i.e. executing a sequence of actions in a particular order. While prior work has…