English
Related papers

Related papers: A Dual Prompt Learning Framework for Few-Shot Dial…

200 papers

Existing dialogue state tracking (DST) models require plenty of labeled data. However, collecting high-quality labels is costly, especially when the number of domains increases. In this paper, we address a practical DST problem that is…

Computation and Language · Computer Science 2020-10-28 Chien-Sheng Wu , Steven Hoi , Caiming Xiong

Few-shot Learning aims to learn and distinguish new categories with a very limited number of available images, presenting a significant challenge in the realm of deep learning. Recent researchers have sought to leverage the additional…

Computer Vision and Pattern Recognition · Computer Science 2024-03-26 Chunpeng Zhou , Haishuai Wang , Xilu Yuan , Zhi Yu , Jiajun Bu

In dialogue state tracking, dialogue history is a crucial material, and its utilization varies between different models. However, no matter how the dialogue history is used, each existing model uses its own consistent dialogue history…

Computation and Language · Computer Science 2022-05-23 Jinyu Guo , Kai Shuang , Jijie Li , Zihan Wang , Yixuan Liu

Recently, data-driven task-oriented dialogue systems have achieved promising performance in English. However, developing dialogue systems that support low-resource languages remains a long-standing challenge due to the absence of…

Computation and Language · Computer Science 2019-11-22 Zihan Liu , Genta Indra Winata , Zhaojiang Lin , Peng Xu , Pascale Fung

We highlight a practical yet rarely discussed problem in dialogue state tracking (DST), namely handling unknown slot values. Previous approaches generally assume predefined candidate lists and thus are not designed to output unknown values,…

Computation and Language · Computer Science 2018-05-07 Puyang Xu , Qi Hu

Learning from large-scale pre-trained models with strong generalization ability has shown remarkable success in a wide range of downstream tasks recently, but it is still underexplored in the challenging few-shot class-incremental learning…

Computer Vision and Pattern Recognition · Computer Science 2025-08-14 Linpu He , Yanan Li , Bingze Li , Elvis Han Cui , Donghui Wang

A challenge in the Dialogue State Tracking (DST) field is adapting models to new domains without using any supervised data, zero-shot domain adaptation. Parameter-Efficient Transfer Learning (PETL) has the potential to address this problem…

Computation and Language · Computer Science 2023-06-09 Taha Aksu , Min-Yen Kan , Nancy F. Chen

A desirable dialog system should be able to continually learn new skills without forgetting old ones, and thereby adapt to new domains or tasks in its life cycle. However, continually training a model often leads to a well-known…

Computation and Language · Computer Science 2022-03-15 Qi Zhu , Bing Li , Fei Mi , Xiaoyan Zhu , Minlie Huang

Zero-shot transfer learning for Dialogue State Tracking (DST) helps to handle a variety of task-oriented dialogue domains without the cost of collecting in-domain data. Existing works mainly study common data- or model-level augmentation…

Computation and Language · Computer Science 2023-06-02 Qingyue Wang , Liang Ding , Yanan Cao , Yibing Zhan , Zheng Lin , Shi Wang , Dacheng Tao , Li Guo

We demonstrate substantial performance gains in zero-shot dialogue state tracking (DST) by enhancing training data diversity through synthetic data generation. Existing DST datasets are severely limited in the number of application domains…

Computation and Language · Computer Science 2024-06-14 James D. Finch , Jinho D. Choi

Goal-oriented chatbots are essential for automating user tasks, such as booking flights or making restaurant reservations. A key component of these systems is Dialogue State Tracking (DST), which interprets user intent and maintains the…

Computation and Language · Computer Science 2025-03-28 Sejin Lee , Dongha Kim , Min Song

We investigate the problem of multi-domain Dialogue State Tracking (DST) with open vocabulary, which aims to extract the state from the dialogue. Existing approaches usually concatenate previous dialogue state with dialogue history as the…

Computation and Language · Computer Science 2020-10-22 Yan Zeng , Jian-Yun Nie

The effectiveness of prompt learning has been demonstrated in different pre-trained language models. By formulating suitable template and choosing representative label mapping, prompt learning can be used as an efficient knowledge probe.…

Computation and Language · Computer Science 2022-11-01 Jinta Weng , Yue Hu , Jing Qiu , Heyan Huan

The primary purpose of dialogue state tracking (DST), a critical component of an end-to-end conversational system, is to build a model that responds well to real-world situations. Although we often change our minds from time to time during…

Computation and Language · Computer Science 2022-10-13 Takyoung Kim , Yukyung Lee , Hoonsang Yoon , Pilsung Kang , Junseong Bang , Misuk Kim

Pre-trained language models (PLM) have marked a huge leap in neural dialogue modeling. While PLMs are pre-trained on large-scale text corpora, they are usually fine-tuned on scarce dialogue data with specific domain knowledge and dialogue…

Computation and Language · Computer Science 2021-12-14 Xiaodong Gu , Kang Min Yoo , Sang-Woo Lee

Task-oriented dialogue systems aim to help users achieve their goals in specific domains. Recent neural dialogue systems use the entire dialogue history for abundant contextual information accumulated over multiple conversational turns.…

Computation and Language · Computer Science 2021-03-12 Hyunmin Jeon , Gary Geunbae Lee

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…

Computation and Language · Computer Science 2021-06-02 Yinpei Dai , Hangyu Li , Yongbin Li , Jian Sun , Fei Huang , Luo Si , Xiaodan Zhu

State-of-the-art slot filling models for goal-oriented human/machine conversational language understanding systems rely on deep learning methods. While multi-task training of such models alleviates the need for large in-domain annotated…

Artificial Intelligence · Computer Science 2017-07-11 Ankur Bapna , Gokhan Tur , Dilek Hakkani-Tur , Larry Heck

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…

Computation and Language · Computer Science 2022-03-23 Taha Aksu , Zhengyuan Liu , Min-Yen Kan , Nancy F. Chen

Most recently proposed approaches in dialogue state tracking (DST) leverage the context and the last dialogue states to track current dialogue states, which are often slot-value pairs. Although the context contains the complete dialogue…

Computation and Language · Computer Science 2021-07-13 Jingyao Zhou , Haipang Wu , Zehao Lin , Guodun Li , Yin Zhang