Abstract
Graph convolutional networks (GCNs) have been applied recently to text classification and produced an excellent performance. However, existing GCN-based methods do not assume an explicit latent semantic structure of documents, making learned representations less effective and difficult to interpret. They are also transductive in nature, thus cannot handle out-of-graph documents. To address these issues, we propose a novel model named inductive Topic Variational Graph Auto-Encoder (T-VGAE), which incorporates a topic model into variational graph-auto-encoder (VGAE) to capture the hidden semantic information between documents and words. T-VGAE inherits the interpretability of the topic model and the efficient information propagation mechanism of VGAE. It learns probabilistic representations of words and documents by jointly encoding and reconstructing the global word-level graph and bipartite graphs of documents, where each document is considered individually and decoupled from the global correlation graph so as to enable inductive learning. Our experiments on several benchmark datasets show that our method outperforms the existing competitive models on supervised and semi-supervised text classification, as well as unsupervised text representation learning. In addition, it has higher interpretability and is able to deal with unseen documents.- Anthology ID:
- 2021.naacl-main.333
- Volume:
- Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Month:
- June
- Year:
- 2021
- Address:
- Online
- Editors:
- Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, Yichao Zhou
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4218–4227
- Language:
- URL:
- https://aclanthology.org/2021.naacl-main.333
- DOI:
- 10.18653/v1/2021.naacl-main.333
- Cite (ACL):
- Qianqian Xie, Jimin Huang, Pan Du, Min Peng, and Jian-Yun Nie. 2021. Inductive Topic Variational Graph Auto-Encoder for Text Classification. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4218–4227, Online. Association for Computational Linguistics.
- Cite (Informal):
- Inductive Topic Variational Graph Auto-Encoder for Text Classification (Xie et al., NAACL 2021)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2021.naacl-main.333.pdf