paper-with-me

Papers

Decoupling Representation and Knowledge for Few-Shot Intent Classification and Slot Filling

2023-12-21 · Jie Han, Yixiong Zou, Haozhao Wang, Jun Wang, Wei Liu, Yao Wu, Tao Zhang, Ruixuan Li

Few-shot intent classification and slot filling are important but challenging tasks due to the scarcity of finely labeled data. Therefore, current works first train a model on source domains with sufficiently labeled data, and then transfer the model to target domains where only rarely labeled data is available. However, experience transferring as a whole usually suffers from gaps that exist among source domains and target domains. For instance, transferring domain-specific-knowledge-related experience is difficult. To tackle this problem, we propose a new method that explicitly decouples the transferring of general-semantic-representation-related experience and the domain-specific-knowledge-related experience. Specifically, for domain-specific-knowledge-related experience, we design two modules to capture intent-slot relation and slot-slot relation respectively. Extensive experiments on Snips and FewJoint datasets show that our method achieves state-of-the-art performance. The method improves the joint accuracy metric from 27.72% to 42.20% in the 1-shot setting, and from 46.54% to 60.79% in the 5-shot setting.

📄 PDF Abstract BibTeX arXiv:2312.13495

Code (0)

등록된 구현이 없습니다.

Tasks

intent-classificationIntent ClassificationIntent Classification and Slot FillingRelationslot-fillingSlot Filling

Similar Papers 제목 키워드 기반

Instance Relation Learning Network with Label Knowledge Propagation for Few-shot Multi-label Intent Detection

2025-10-09 · Shiman Zhao, Shangyuan Li, Wei Chen, Tengjiao Wang 외 arxiv

Few-shot Multi-label Intent Detection (MID) is crucial for dialogue systems, aiming to detect multiple intents of utterances in low-resource dialogue domains. Previous studies focus on a two-stage pipeline. They first le…

Intent Detection

Representation based meta-learning for few-shot spoken intent recognition

2021-06-29 · Ashish Mittal, Samarth Bharadwaj, Shreya Khare, Saneem Chemmengath 외

Spoken intent detection has become a popular approach to interface with various smart devices with ease. However, such systems are limited to the preset list of intents-terms or commands, which restricts the quick custom…

Classificationintent-classificationIntent ClassificationIntent Detection+2

Generalized zero-shot audio-to-intent classification

2023-11-04 · Veera Raghavendra Elluru, Devang Kulshreshtha, Rohit Paturi, Sravan Bodapati 외

Spoken language understanding systems using audio-only data are gaining popularity, yet their ability to handle unseen intents remains limited. In this study, we propose a generalized zero-shot audio-to-intent classifica…

ClassificationGoal-Oriented Dialogintent-classificationIntent Classification+4

Knowledge Distillation Meets Few-Shot Learning: An Approach for Few-Shot Intent Classification Within and Across Domains

2022-05-01 · NLP4ConvAI (ACL) 2022 5 · Anna Sauer, Shima Asaadi, Fabian Küch

Large Transformer-based natural language understanding models have achieved state-of-the-art performance in dialogue systems. However, scarce labeled data for training, the large model size, and low inference speed hinde…

Cross-Domain Few-Shotcross-domain few-shot learningFew-Shot Learningintent-classification+3

A Simple Meta-learning Paradigm for Zero-shot Intent Classification with Mixture Attention Mechanism

2022-06-05 · Han Liu, Siyang Zhao, Xiaotong Zhang, Feng Zhang 외

Zero-shot intent classification is a vital and challenging task in dialogue systems, which aims to deal with numerous fast-emerging unacquainted intents without annotated training data. To obtain more satisfactory perfor…

Classificationintent-classificationIntent ClassificationMeta-Learning+3