paper-with-me

Papers

Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Tracking

2020-05-02 · ACL 2020 6 · Giovanni Campagna, Agata Foryciarz, Mehrad Moradshahi, Monica S. Lam

Zero-shot transfer learning for multi-domain dialogue state tracking can allow us to handle new domains without incurring the high cost of data acquisition. This paper proposes new zero-short transfer learning technique for dialogue state tracking where the in-domain training data are all synthesized from an abstract dialogue model and the ontology of the domain. We show that data augmentation through synthesized data can improve the accuracy of zero-shot learning for both the TRADE model and the BERT-based SUMBT model on the MultiWOZ 2.1 dataset. We show training with only synthesized in-domain data on the SUMBT model can reach about 2/3 of the accuracy obtained with the full training dataset. We improve the zero-shot learning state of the art on average across domains by 21%.

📄 PDF Abstract BibTeX arXiv:2005.00891

Code (1)

stanford-oval/zero-shot-multiwoz-acl2020 공식 구현

Tasks

Data AugmentationDialogue State TrackingMulti-domain Dialogue State TrackingTransfer LearningZero-Shot Learning

Similar Papers 제목 키워드 기반

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents

2025-05-27 · Haiyun Li, Zhiyong Wu, XiaoFeng Xie, Jingran Xie 외

Voice cloning (VC)-resistant watermarking is an emerging technique for tracing and preventing unauthorized cloning. Existing methods effectively trace traditional VC models by training them on watermarked audio but fail …

Voice Cloning

Zero-shot Learning via Shared-Reconstruction-Graph Pursuit

2017-11-20 · Bo Zhao, Xinwei Sun, Yuan YAO, Yizhou Wang

Zero-shot learning (ZSL) aims to recognize objects from novel unseen classes without any training data. Recently, structure-transfer based methods are proposed to implement ZSL by transferring structural knowledge from t…

ClusteringGeneralized Zero-Shot LearningTransfer LearningZero-Shot Learning

Improving Zero-Shot Generalization for CLIP with Synthesized Prompts

2023-07-14 · ICCV 2023 1 · Zhengbo Wang, Jian Liang, Ran He, Nan Xu 외

With the growing interest in pretrained vision-language models like CLIP, recent research has focused on adapting these models to downstream tasks. Despite achieving promising results, most existing methods require label…

Generalized Zero-Shot LearningTransfer LearningZero-shot GeneralizationZero-Shot Learning

EmergentBridge: Improving Zero-Shot Cross-Modal Transfer in Unified Multimodal Embedding Models

2026-04-13 · Jincheng Xie, Xingchen Xiao, Runheng Liu, Zhongyi Huang 외 arxiv

Unified multimodal embedding spaces underpin practical applications such as cross-modal retrieval and zero-shot recognition. In many real deployments, however, supervision is available only for a small subset of modality…

Cross-Modal Retrieval

Neuro-symbolic Zero-Shot Code Cloning with Cross-Language Intermediate Representation

2023-04-26 · Krishnam Hasija, Shrishti Pradhan, Manasi Patwardhan, Raveendra Kumar Medicherla 외

In this paper, we define a neuro-symbolic approach to address the task of finding semantically similar clones for the codes of the legacy programming language COBOL, without training data. We define a meta-model that is …

C++ codeCode Search