Výsledky vyhledávání - "Liu, JunLong"

Report

A3S: A General Active Clustering Method with Pairwise Constraints

Autor: Deng, Xun, Liu, Junlong, Zhong, Han, Feng, Fuli, Shen, Chen, He, Xiangnan, Ye, Jieping, Wang, Zheng

Active clustering aims to boost the clustering performance by integrating human-annotated pairwise constraints through strategic querying. Conventional approaches with semi-supervised clustering schemes encounter high query costs when applied to larg

Externí odkaz: http://arxiv.org/abs/2407.10196

Zobrazit plný text záznamu

Report

Self-Adaptive Reconstruction with Contrastive Learning for Unsupervised Sentence Embeddings

Autor: Liu, Junlong, Shang, Xichen, Feng, Huawen, Zheng, Junhao, Ma, Qianli

Unsupervised sentence embeddings task aims to convert sentences to semantic vector representations. Most previous works directly use the sentence representations derived from pretrained language models. However, due to the token bias in pretrained la

Externí odkaz: http://arxiv.org/abs/2402.15153

Zobrazit plný text záznamu

Report

Preserving Commonsense Knowledge from Pre-trained Language Models via Causal Inference

Autor: Zheng, Junhao, Ma, Qianli, Qiu, Shengjie, Wu, Yue, Ma, Peitian, Liu, Junlong, Feng, Huawen, Shang, Xichen, Chen, Haibin

Fine-tuning has been proven to be a simple and effective technique to transfer the learned knowledge of Pre-trained Language Models (PLMs) to downstream tasks. However, vanilla fine-tuning easily overfits the target data and degrades the generalizati

Externí odkaz: http://arxiv.org/abs/2306.10790

Zobrazit plný text záznamu

Report

Self-Learning Symmetric Multi-view Probabilistic Clustering

Autor: Liu, Junjie, Liu, Junlong, Jiang, Rongxin, Chen, Yaowu, Shen, Chen, Ye, Jieping

Multi-view Clustering (MVC) has achieved significant progress, with many efforts dedicated to learn knowledge from multiple views. However, most existing methods are either not applicable or require additional steps for incomplete MVC. Such a limitat

Externí odkaz: http://arxiv.org/abs/2305.07307

Zobrazit plný text záznamu

Report

Pair-Based Joint Encoding with Relational Graph Convolutional Networks for Emotion-Cause Pair Extraction

Autor: Liu, Junlong, Shang, Xichen, Ma, Qianli

Emotion-cause pair extraction (ECPE) aims to extract emotion clauses and corresponding cause clauses, which have recently received growing attention. Previous methods sequentially encode features with a specified order. They first encode the emotion

Externí odkaz: http://arxiv.org/abs/2212.01844

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání