SemanticGraph2Vec: Semantic graph embedding for text representation
Graph embedding is an important representational technique that aims to maintain the structure of a graph while learning low-dimensional representations of its vertices. Semantic relationships between vertices contain essential information regarding the meaning of the represented graph. However, mos...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-03-01
|
| Series: | Array |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590005623000012 |
| _version_ | 1797904261442437120 |
|---|---|
| author | Wael Etaiwi Arafat Awajan |
| author_facet | Wael Etaiwi Arafat Awajan |
| author_sort | Wael Etaiwi |
| collection | DOAJ |
| description | Graph embedding is an important representational technique that aims to maintain the structure of a graph while learning low-dimensional representations of its vertices. Semantic relationships between vertices contain essential information regarding the meaning of the represented graph. However, most graph embedding methods do not consider the semantic relationships during the learning process. In this paper, we propose a novel semantic graph embedding approach, called SemanticGraph2Vec. SemanticGraph2Vec learns mappings of vertices into low-dimensional feature spaces that consider the most important semantic relationships between graph vertices. The proposed approach extends and enhances prior work based on a set of random walks of graph vertices by using semantic walks instead of random walks which provides more useful embeddings for text graphs. A set of experiments are conducted to evaluate the performance of SemanticGraph2Vec. SemanticGraph2Vec is employed on a part-of-speech tagging task. Experimental results demonstrate that SemanticGraph2Vec outperforms two state-of-the-art baselines methods in terms of precision and F1 score. |
| first_indexed | 2024-04-10T09:46:05Z |
| format | Article |
| id | doaj.art-0e622a8fe519433da18c34c0b472185c |
| institution | Directory Open Access Journal |
| issn | 2590-0056 |
| language | English |
| last_indexed | 2024-04-10T09:46:05Z |
| publishDate | 2023-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Array |
| spelling | doaj.art-0e622a8fe519433da18c34c0b472185c2023-02-17T04:55:36ZengElsevierArray2590-00562023-03-0117100276SemanticGraph2Vec: Semantic graph embedding for text representationWael Etaiwi0Arafat Awajan1Corresponding author.; Princess Sumaya University for Technology, Amman, JordanPrincess Sumaya University for Technology, Amman, JordanGraph embedding is an important representational technique that aims to maintain the structure of a graph while learning low-dimensional representations of its vertices. Semantic relationships between vertices contain essential information regarding the meaning of the represented graph. However, most graph embedding methods do not consider the semantic relationships during the learning process. In this paper, we propose a novel semantic graph embedding approach, called SemanticGraph2Vec. SemanticGraph2Vec learns mappings of vertices into low-dimensional feature spaces that consider the most important semantic relationships between graph vertices. The proposed approach extends and enhances prior work based on a set of random walks of graph vertices by using semantic walks instead of random walks which provides more useful embeddings for text graphs. A set of experiments are conducted to evaluate the performance of SemanticGraph2Vec. SemanticGraph2Vec is employed on a part-of-speech tagging task. Experimental results demonstrate that SemanticGraph2Vec outperforms two state-of-the-art baselines methods in terms of precision and F1 score.http://www.sciencedirect.com/science/article/pii/S2590005623000012DeepWalkGraph embeddingSemantic graphRandom walk |
| spellingShingle | Wael Etaiwi Arafat Awajan SemanticGraph2Vec: Semantic graph embedding for text representation Array DeepWalk Graph embedding Semantic graph Random walk |
| title | SemanticGraph2Vec: Semantic graph embedding for text representation |
| title_full | SemanticGraph2Vec: Semantic graph embedding for text representation |
| title_fullStr | SemanticGraph2Vec: Semantic graph embedding for text representation |
| title_full_unstemmed | SemanticGraph2Vec: Semantic graph embedding for text representation |
| title_short | SemanticGraph2Vec: Semantic graph embedding for text representation |
| title_sort | semanticgraph2vec semantic graph embedding for text representation |
| topic | DeepWalk Graph embedding Semantic graph Random walk |
| url | http://www.sciencedirect.com/science/article/pii/S2590005623000012 |
| work_keys_str_mv | AT waeletaiwi semanticgraph2vecsemanticgraphembeddingfortextrepresentation AT arafatawajan semanticgraph2vecsemanticgraphembeddingfortextrepresentation |