Abstract
Network embeddings, which learns low-dimensional representations for each vertex in a large-scale network, have received considerable attention in recent years. For a wide range of applications, vertices in a network are typically accompanied by rich textual information such as user profiles, paper abstracts, etc. In this paper, we propose to incorporate semantic features into network embeddings by matching important words between text sequences for all pairs of vertices. We introduce an word-by-word alignment framework that measures the compatibility of embeddings between word pairs, and then adaptively accumulates these alignment features with a simple yet effective aggregation function. In experiments, we evaluate the proposed framework on three real-world benchmarks for downstream tasks, including link prediction and multi-label vertex classification. The experimental results demonstrate that our model outperforms state-of-the-art network embedding methods by a large margin.- Anthology ID:
- D18-1209
- Volume:
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Month:
- October-November
- Year:
- 2018
- Address:
- Brussels, Belgium
- Editors:
- Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1829–1838
- Language:
- URL:
- https://aclanthology.org/D18-1209
- DOI:
- 10.18653/v1/D18-1209
- Cite (ACL):
- Dinghan Shen, Xinyuan Zhang, Ricardo Henao, and Lawrence Carin. 2018. Improved Semantic-Aware Network Embedding with Fine-Grained Word Alignment. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 1829–1838, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- Improved Semantic-Aware Network Embedding with Fine-Grained Word Alignment (Shen et al., EMNLP 2018)
- PDF:
- https://preview.aclanthology.org/emnlp22-frontmatter/D18-1209.pdf