paper-with-me

Papers

Vec2GC -- A Graph Based Clustering Method for Text Representations

2021-04-15 · Rajesh N Rao, Manojit Chakraborty

NLP pipelines with limited or no labeled data, rely on unsupervised methods for document processing. Unsupervised approaches typically depend on clustering of terms or documents. In this paper, we introduce a novel clustering algorithm, Vec2GC (Vector to Graph Communities), an end-to-end pipeline to cluster terms or documents for any given text corpus. Our method uses community detection on a weighted graph of the terms or documents, created using text representation learning. Vec2GC clustering algorithm is a density based approach, that supports hierarchical clustering as well.

📄 PDF Abstract BibTeX arXiv:2104.09439

Code (2)

niteshjindal170988/workflow-docs-search
niteshjindal170988/workflow-docs-search--word-embeddings

Tasks

ClusteringCommunity DetectionRepresentation Learning

Similar Papers 제목 키워드 기반

Representation Learning for Short Text Clustering

2021-09-21 · Hui Yin, XiangYu Song, Shuiqiao Yang, Guangyan Huang 외

Effective representation learning is critical for short text clustering due to the sparse, high-dimensional and noise attributes of short text corpus. Existing pre-trained models (e.g., Word2vec and BERT) have greatly im…

ClusteringRepresentation LearningShort Text ClusteringText Clustering

Multi-level Graph Subspace Contrastive Learning for Hyperspectral Image Clustering

2024-04-08 · Jingxin Wang, Renxiang Guan, Kainan Gao, Zihao Li 외

Hyperspectral image (HSI) clustering is a challenging task due to its high complexity. Despite subspace clustering shows impressive performance for HSI, traditional methods tend to ignore the global-local interaction in …

ClusteringContrastive Learninghyperspectral image clusteringImage Clustering

Unsupervised lexicon learning from speech is limited by representations rather than clustering

2025-10-10 · Danel Slabbert, Simon Malan, Herman Kamper arxiv

Zero-resource word segmentation and clustering systems aim to tokenise speech into word-like units without access to text labels. Despite progress, the induced lexicons are still far from perfect. In an idealised setting…

Graph Clustering

Automatic Biomedical Term Clustering by Learning Fine-grained Term Representations

2022-04-01 · BioNLP (ACL) 2022 5 · Sihang Zeng, Zheng Yuan, Sheng Yu

Term clustering is important in biomedical knowledge graph construction. Using similarities between terms embedding is helpful for term clustering. State-of-the-art term embeddings leverage pretrained language models to …

ClusteringContrastive Learninggraph constructionKnowledge Graphs

Subspace Co-clustering with Two-Way Graph Convolution

2022-02-01 · CIKM '22: Proceedings of the 31st ACM International Conference on Information & Knowledge Management 2022 2 · Chakib Fettal, Lazhar Labiod, Mohamed Nadif

Subspace clustering aims to cluster high dimensional data lying in a union of low-dimensional subspaces. It has shown good results on the task of image clustering but text clustering, using documentterm matrices, proved …

ClusteringImage ClusteringText Clustering