Related papers: Sequence-to-Sequence Learning for Task-oriented Di…
Human dialogues are scenario-based and appropriate responses generally relate to the latent context knowledge entailed by the specific scenario. To enable responses that are more meaningful and context-specific, we propose to improve…
Most prior work on task-oriented dialogue systems are restricted to limited coverage of domain APIs. However, users oftentimes have requests that are out of the scope of these APIs. This work focuses on responding to these…
Recently, pre-training methods have shown remarkable success in task-oriented dialog (TOD) systems. However, most existing pre-trained models for TOD focus on either dialog understanding or dialog generation, but not both. In this paper, we…
End-to-end task-oriented dialogue systems aim to generate system responses directly from plain text inputs. There are two challenges for such systems: one is how to effectively incorporate external knowledge bases (KBs) into the learning…
Task-oriented dialog systems have witnessed substantial progress due to conversational pre-training techniques. Yet, two significant challenges persist. First, most systems primarily utilize the latest turn's state label for the generator.…
This paper presents a novel application of large language models in user simulation for task-oriented dialog systems, specifically focusing on an in-context learning approach. By harnessing the power of these models, the proposed approach…
This paper presents a recurrent hybrid model and training procedure for task-oriented dialogue systems based on Deep Recurrent Q-Networks (DRQN). The model copes with both tasks required for Dialogue Management: State Tracking and Decision…
In task-oriented dialogue systems the dialogue state tracker (DST) component is responsible for predicting the state of the dialogue based on the dialogue history. Current DST approaches rely on a predefined domain ontology, a fact that…
Dialogue systems dealing with multi-domain tasks are highly required. How to record the state remains a key problem in a task-oriented dialogue system. Normally we use human-defined features as dialogue states and apply a state tracker to…
The standard task-oriented dialogue pipeline uses intent classification and slot-filling to interpret user utterances. While this approach can handle a wide range of queries, it does not extract the information needed to handle more complex…
This ability to learn consecutive tasks without forgetting how to perform previously trained problems is essential for developing an online dialogue system. This paper proposes an effective continual learning for the task-oriented dialogue…
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…
We introduce end-to-end neural network based models for simulating users of task-oriented dialogue systems. User simulation in dialogue systems is crucial from two different perspectives: (i) automatic evaluation of different dialogue…
Spatio-temporal deep learning models aims to utilize useful patterns in such data to support tasks like prediction. However, previous deep learning models designed for specific tasks typically require separate training for each use case,…
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…
The reasoning capability of large language models (LLMs), defined as their ability to analyze, infer, and make decisions based on input information, is essential for building intelligent task-oriented dialogue systems. However, existing…
End-to-end task-oriented dialog systems usually suffer from the challenge of incorporating knowledge bases. In this paper, we propose a novel yet simple end-to-end differentiable model called memory-to-sequence (Mem2Seq) to address this…
Building an intelligent dialogue system with the ability to select a proper response according to a multi-turn context is a great challenging task. Existing studies focus on building a context-response matching model with various neural…
In this work, we propose contextual language models that incorporate dialog level discourse information into language modeling. Previous works on contextual language model treat preceding utterances as a sequence of inputs, without…
Previous dialogue summarization datasets mainly focus on open-domain chitchat dialogues, while summarization datasets for the broadly used task-oriented dialogue haven't been explored yet. Automatically summarizing such task-oriented…