GAE-Based Document Embedding Method for Clustering
Document embedding methods for clustering using deep neural networks have been proposed recently. However, the existing deep neural network-based document embedding methods for clustering have a problem of either generating document embeddings dependent on a given number of document clusters or gene...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9982435/ |
| _version_ | 1828164073277095936 |
|---|---|
| author | Sungwon Jung Sangmin Ka |
| author_facet | Sungwon Jung Sangmin Ka |
| author_sort | Sungwon Jung |
| collection | DOAJ |
| description | Document embedding methods for clustering using deep neural networks have been proposed recently. However, the existing deep neural network-based document embedding methods for clustering have a problem of either generating document embeddings dependent on a given number of document clusters or generating document embeddings that do not take into account the characteristic of high similarity between documents belonging to the same document cluster. In this paper, we propose a new document embedding method for clustering by using a graph autoencoder. To this end, we construct an undirected and weighted sparse graph from a set of documents wherein each document is represented by a node, and all the weighted edges created in the graph have high cosine similarities between the two end nodes. We then apply the proposed graph autoencoder to the graph to compute node embedding vectors. Each node embedding vector in the graph is used as a document embedding vector. This paper presents in-depth experimental analyses of the proposed method. Experimental results on various real document data sets demonstrate that the proposed approach affords the significant performance improvement over the existing document embedding methods. |
| first_indexed | 2024-04-12T01:20:48Z |
| format | Article |
| id | doaj.art-3ebb880c9ffd4f068bd4f8e75d0ceeb9 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-12T01:20:48Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-3ebb880c9ffd4f068bd4f8e75d0ceeb92022-12-22T03:53:48ZengIEEEIEEE Access2169-35362022-01-011013008913009610.1109/ACCESS.2022.32285489982435GAE-Based Document Embedding Method for ClusteringSungwon Jung0https://orcid.org/0000-0002-5332-5947Sangmin Ka1https://orcid.org/0000-0001-7572-022XDepartment of Computer Science and Engineering, Sogang University, Seoul, South KoreaDepartment of Computer Science and Engineering, Sogang University, Seoul, South KoreaDocument embedding methods for clustering using deep neural networks have been proposed recently. However, the existing deep neural network-based document embedding methods for clustering have a problem of either generating document embeddings dependent on a given number of document clusters or generating document embeddings that do not take into account the characteristic of high similarity between documents belonging to the same document cluster. In this paper, we propose a new document embedding method for clustering by using a graph autoencoder. To this end, we construct an undirected and weighted sparse graph from a set of documents wherein each document is represented by a node, and all the weighted edges created in the graph have high cosine similarities between the two end nodes. We then apply the proposed graph autoencoder to the graph to compute node embedding vectors. Each node embedding vector in the graph is used as a document embedding vector. This paper presents in-depth experimental analyses of the proposed method. Experimental results on various real document data sets demonstrate that the proposed approach affords the significant performance improvement over the existing document embedding methods.https://ieeexplore.ieee.org/document/9982435/Document embeddingtext embeddingdocument clusteringgraph autoencodergraph CNNautoencoder |
| spellingShingle | Sungwon Jung Sangmin Ka GAE-Based Document Embedding Method for Clustering IEEE Access Document embedding text embedding document clustering graph autoencoder graph CNN autoencoder |
| title | GAE-Based Document Embedding Method for Clustering |
| title_full | GAE-Based Document Embedding Method for Clustering |
| title_fullStr | GAE-Based Document Embedding Method for Clustering |
| title_full_unstemmed | GAE-Based Document Embedding Method for Clustering |
| title_short | GAE-Based Document Embedding Method for Clustering |
| title_sort | gae based document embedding method for clustering |
| topic | Document embedding text embedding document clustering graph autoencoder graph CNN autoencoder |
| url | https://ieeexplore.ieee.org/document/9982435/ |
| work_keys_str_mv | AT sungwonjung gaebaseddocumentembeddingmethodforclustering AT sangminka gaebaseddocumentembeddingmethodforclustering |