Výsledky vyhledávání - "Cheng, Zifeng"

Report

A Debiased Nearest Neighbors Framework for Multi-Label Text Classification

Autor: Cheng, Zifeng, Jiang, Zhiwei, Yin, Yafeng, Chen, Zhaoling, Wang, Cong, Ge, Shiping, Huang, Qiguo, Gu, Qing

Multi-Label Text Classification (MLTC) is a practical yet challenging task that involves assigning multiple non-exclusive labels to each document. Previous studies primarily focus on capturing label correlations to assist label prediction by introduc

Externí odkaz: http://arxiv.org/abs/2408.03202

Zobrazit plný text záznamu

Report

Multi-Prompting Decoder Helps Better Language Understanding

Autor: Cheng, Zifeng, Chen, Zhaoling, Jiang, Zhiwei, Yin, Yafeng, Ge, Shiping, Liu, Yuliang, Gu, Qing

Recent Pre-trained Language Models (PLMs) usually only provide users with the inference APIs, namely the emerging Model-as-a-Service (MaaS) setting. To adapt MaaS PLMs to downstream tasks without accessing their parameters and gradients, some existin

Externí odkaz: http://arxiv.org/abs/2406.06279

Zobrazit plný text záznamu

Report

Unifying Token and Span Level Supervisions for Few-Shot Sequence Labeling

Autor: Cheng, Zifeng, Zhou, Qingyu, Jiang, Zhiwei, Zhao, Xuemin, Cao, Yunbo, Gu, Qing

Few-shot sequence labeling aims to identify novel classes based on only a few labeled samples. Existing methods solve the data scarcity problem mainly by designing token-level or span-level labeling models based on metric learning. However, these met

Externí odkaz: http://arxiv.org/abs/2307.07946

Zobrazit plný text záznamu

Report

Controlling Class Layout for Deep Ordinal Classification via Constrained Proxies Learning

Autor: Wang, Cong, Jiang, Zhiwei, Yin, Yafeng, Cheng, Zifeng, Ge, Shiping, Gu, Qing

For deep ordinal classification, learning a well-structured feature space specific to ordinal classification is helpful to properly capture the ordinal nature among classes. Intuitively, when Euclidean distance metric is used, an ideal ordinal layout

Externí odkaz: http://arxiv.org/abs/2303.00396

Zobrazit plný text záznamu

Report

Learning to Classify Open Intent via Soft Labeling and Manifold Mixup

Autor: Cheng, Zifeng, Jiang, Zhiwei, Yin, Yafeng, Wang, Cong, Gu, Qing

Open intent classification is a practical yet challenging task in dialogue systems. Its objective is to accurately classify samples of known intents while at the same time detecting those of open (unknown) intents. Existing methods usually use outlie

Externí odkaz: http://arxiv.org/abs/2204.07804

Zobrazit plný text záznamu