Semantic Label Representations with Lbl2Vec - A Similarity-Based Approach for Unsupervised Text Classification
In this paper, we evaluate the Lbl2Vec approach for unsupervised text document classification. Lbl2Vec requires only a small number of keywords describing the respective classes to create semantic label representations. For classification, Lbl2Vec uses cosine similarities between label and document representations, but no annotation information. We show that Lbl2Vec significantly outperforms common unsupervised text classification approaches and a widely used zero-shot text classification approach. Furthermore, we show that using more precise keywords can significantly improve the classification results of similarity-based text classification approaches.
| Attribute | Value |
|---|---|
| Address | Springer, Cham |
| Authors | Tim Schopf , Dr. Daniel Braun , Prof. Dr. Florian Matthes |
| Citation | @InProceedings{10.1007/978-3-031-24197-0_4, author="Schopf, Tim and Braun, Daniel and Matthes, Florian", editor="Marchiori, Massimo and Dom{\'i}nguez Mayo, Francisco Jos{\'e} and Filipe, Joaquim", title="Semantic Label Representations with Lbl2Vec: A Similarity-Based Approach for Unsupervised Text Classification", booktitle="Web Information Systems and Technologies", year="2023", publisher="Springer International Publishing", address="Cham", pages="59--73", abstract="In this paper, we evaluate the Lbl2Vec approach for unsupervised text document classification. Lbl2Vec requires only a small number of keywords describing the respective classes to create semantic label representations. For classification, Lbl2Vec uses cosine similarities between label and document representations, but no annotation information. We show that Lbl2Vec significantly outperforms common unsupervised text classification approaches and a widely used zero-shot text classification approach. Furthermore, we show that using more precise keywords can significantly improve the classification results of similarity-based text classification approaches.", isbn="978-3-031-24197-0" } |
| Key | Sc23a |
| Research project | |
| Title | Semantic Label Representations with Lbl2Vec - A Similarity-Based Approach for Unsupervised Text Classification |
| Type of publication | Conference |
| Year | 2023 |
| Publication URL | https://doi.org/10.1007/978-3-031-24197-0_4 |
| Acronym | |
| Project | |
| Team members |