中文
相关论文

相关论文: Approaching Dialogue State Tracking via Aligning S…

200 篇论文

Dialogue State Tracking (DST), a key component of task-oriented conversation systems, represents user intentions by determining the values of pre-defined slots in an ongoing dialogue. Existing approaches use hand-crafted templates and…

计算与语言 · 计算机科学 2023-10-24 Praveen Venkateswaran , Evelyn Duesterwald , Vatche Isahagian

The recent advancements in large language models (LLMs) have revolutionized the field of natural language processing, progressively broadening their scope to multimodal perception and generation. However, effectively integrating listening…

In dialogue transcription pipelines, Large Language Models (LLMs) are frequently employed in post-processing to improve grammar, punctuation, and readability. We explore a complementary post-processing step: enriching transcribed dialogues…

计算与语言 · 计算机科学 2025-09-10 Thomas Thebaud , Yen-Ju Lu , Matthew Wiesner , Peter Viechnicki , Najim Dehak

We present an approach to build Large Language Model (LLM) based slot-filling system to perform Dialogue State Tracking in conversational assistants serving across a wide variety of industry-grade applications. Key requirements of this…

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…

计算与语言 · 计算机科学 2023-06-21 Haoning Zhang , Junwei Bao , Haipeng Sun , Youzheng Wu , Wenye Li , Shuguang Cui , Xiaodong He

Dialogue state tracking (DST) is a component of the task-oriented dialogue system. It is responsible for extracting and managing slot values according to dialogue utterances, where each slot represents an essential part of the information…

计算与语言 · 计算机科学 2022-04-26 Zhoujian Sun , Zhengxing Huang , Nai Ding

Existing dialog state tracking (DST) models are trained with dialog data in a random order, neglecting rich structural information in a dataset. In this paper, we propose to use curriculum learning (CL) to better leverage both the…

计算与语言 · 计算机科学 2021-06-02 Yinpei Dai , Hangyu Li , Yongbin Li , Jian Sun , Fei Huang , Luo Si , Xiaodan Zhu

This paper presents a novel approach for multi-task learning of language understanding (LU) and dialogue state tracking (DST) in task-oriented dialogue systems. Multi-task training enables the sharing of the neural network layers…

计算与语言 · 计算机科学 2018-11-14 Abhinav Rastogi , Raghav Gupta , Dilek Hakkani-Tur

Collecting and annotating task-oriented dialogues is time-consuming and costly; thus, zero and few shot learning could greatly benefit dialogue state tracking (DST). In this work, we propose an in-context learning (ICL) framework for…

计算与语言 · 计算机科学 2022-10-27 Yushi Hu , Chia-Hsuan Lee , Tianbao Xie , Tao Yu , Noah A. Smith , Mari Ostendorf

Speech language models (SpeechLMs) accept speech input and produce speech output, allowing for more natural human-computer interaction compared to text-based large language models (LLMs). Traditional approaches for developing SpeechLMs are…

计算与语言 · 计算机科学 2024-12-03 Aohan Zeng , Zhengxiao Du , Mingdao Liu , Lei Zhang , Shengmin Jiang , Yuxiao Dong , Jie Tang

Dialog state tracking (DST) is a crucial component in a task-oriented dialog system for conversational information access. A common practice in current dialog systems is to define the dialog state by a set of slot-value pairs. Such…

计算与语言 · 计算机科学 2018-11-06 Yinpei Dai , Zhijian Ou , Dawei Ren , Pengfei Yu

User simulators are essential to conversational AI, enabling scalable agent development and evaluation through simulated interactions. While current Large Language Models (LLMs) have advanced user simulation capabilities, we reveal that…

计算与语言 · 计算机科学 2026-03-10 Shuhaib Mehri , Xiaocheng Yang , Takyoung Kim , Gokhan Tur , Shikib Mehri , Dilek Hakkani-Tür

Dialogue State Tracking is central to multi-domain task-oriented dialogue systems, responsible for extracting information from user utterances. We present a novel hybrid architecture that augments GPT-2 with representations derived from…

计算与语言 · 计算机科学 2021-09-24 Weizhe Lin , Bo-Hsiang Tseng , Bill Byrne

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…

计算与语言 · 计算机科学 2019-11-04 Vevake Balaraman , Bernardo Magnini

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…

计算与语言 · 计算机科学 2024-06-14 Ming Gu , Yan Yang

Dialogue state tracking is the core part of a spoken dialogue system. It estimates the beliefs of possible user's goals at every dialogue turn. However, for most current approaches, it's difficult to scale to large dialogue domains. They…

计算与语言 · 计算机科学 2018-10-24 Liliang Ren , Kaige Xie , Lu Chen , Kai Yu

Dialogue state tracking models play an important role in a task-oriented dialogue system. However, most of them model the slot types conditionally independently given the input. We discover that it may cause the model to be confused by slot…

计算与语言 · 计算机科学 2021-11-16 Ting-Rui Chiang , Yi-Ting Yeh

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…

计算与语言 · 计算机科学 2019-09-27 Chenguang Zhu , Michael Zeng , Xuedong Huang

Task-Oriented Dialogue (TOD) systems are designed to carry out specific tasks by tracking dialogue states and generating appropriate responses to help users achieve defined goals. Recently, end-to-end dialogue models pre-trained based on…

计算与语言 · 计算机科学 2023-06-01 Namo Bang , Jeehyun Lee , Myoung-Wan Koo

Task-oriented dialogue systems based on Large Language Models (LLMs) have gained increasing attention across various industries and achieved significant results. Current approaches condense complex procedural workflows into a single agent…

多智能体系统 · 计算机科学 2025-05-21 Zihao Feng , Xiaoxue Wang , Bowen Wu , Weihong Zhong , Zhen Xu , Hailong Cao , Tiejun Zhao , Ying Li , Baoxun Wang