Grünefeld, Nils: Explaining and Applying Graph Neural Networks on Text. Hannover : Gottfried Wilhelm Leibniz Universität Hannover, Bachelor Thesis, 2022, 44 S. DOI: http://doi.org/10.15488/11964
Abstract: | |
Text classification is an essential task in natural language processing. While graph neural networks (GNNs) have successfully been applied to this problem both through graph classification and node classification approaches, their typical applications suffer from several issues. In the graph classification case, common graph construction techniques tend to leave out syntactic information. In the node classification case, most widespread datasets and applications tend to suffer from encoding relatively little information in the chosen node features. Finally, there are great benefits to be gained from combining the two GNN approaches. To tackle these concerns, we propose DepNet, a two-stage framework for text classification using GNN models. In the first stage we replace current graph construction methods by utilizing syntactic dependency parsing in order to include as much syntactic information in the GNN input as possible. In the second stage we combine both graph classification and node classification methods by utilizing the former to produce node embeddings for the latter, maximizing the potential of GNNs for text classification. We find that this technique significantly improves the performance of both graph classification and node classification approaches to text classification. | |
License of this version: | CC BY 3.0 DE |
Document Type: | BachelorThesis |
Publishing status: | publishedVersion |
Issue Date: | 2022 |
Appears in Collections: | Fakultät für Elektrotechnik und Informatik |
pos. | country | downloads | ||
---|---|---|---|---|
total | perc. | |||
1 | Germany | 202 | 54.59% | |
2 | United States | 55 | 14.86% | |
3 | China | 24 | 6.49% | |
4 | No geo information available | 11 | 2.97% | |
5 | India | 11 | 2.97% | |
6 | Netherlands | 10 | 2.70% | |
7 | Iran, Islamic Republic of | 5 | 1.35% | |
8 | Hong Kong | 5 | 1.35% | |
9 | Italy | 4 | 1.08% | |
10 | France | 4 | 1.08% | |
other countries | 39 | 10.54% |
Hinweis
Zur Erhebung der Downloadstatistiken kommen entsprechend dem „COUNTER Code of Practice for e-Resources“ international anerkannte Regeln und Normen zur Anwendung. COUNTER ist eine internationale Non-Profit-Organisation, in der Bibliotheksverbände, Datenbankanbieter und Verlage gemeinsam an Standards zur Erhebung, Speicherung und Verarbeitung von Nutzungsdaten elektronischer Ressourcen arbeiten, welche so Objektivität und Vergleichbarkeit gewährleisten sollen. Es werden hierbei ausschließlich Zugriffe auf die entsprechenden Volltexte ausgewertet, keine Aufrufe der Website an sich.