.png){kind=icon}
返回
Contrastive author-aware text clustering
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2022.108787.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In the era of User Generated Content (UGC), authors (IDs) of texts widely exist and play a key role in determining the topic categories of texts. Existing text clustering effort s are mainly attributed to utiliz-ing textual information, but the effect of authors on text clustering remains largely underexplored. To mitigate this issue, we propose a novel Contrastive Author-aware Text clustering approach, dubbed as CAT. CAT injects author information not only in characterizing texts through representations but also in pushing or pulling text representations of different authors through contrastive learning, which is rarely adopted by text clustering. Specifically, the developed contrastive learning method conducts both cluster-instance contrast by the text representation augmentation and instance-instance contrast by the multi-view representations. We perform comprehensive experiments on three public datasets, demonstrating that CAT largely outperforms strong competitive text clustering baselines and validating the effectiveness of the CAT's main components. (c) 2022 Elsevier Ltd. All rights reserved.
Keyword:
Text clustering
Contrastive learning
Representation learning
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Multi-view subspace clustering via simultaneously learning the representation tensor and affinity matrix.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Discriminative subspace matrix factorization for multiview data clusteringPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Deep k-Means: Jointly clustering with k-Means and learning representations深度k-means: 使用k-means和学习表示进行联合聚类
OAAI
OAAI分享收藏 没有更多内容
没有更多内容