From Nguyen et al. (2015):
"Recently, with the emerging interests of the community in deep learning, CNNs have been revived and effectively applied in various NLP tasks, including semantic parsing (Yih et al., 2014), search query retrieval (Shen et al., 2014), sentence modeling and classification (Kalchbrenner et al., 2014; Kim, 2014), name tagging and semantic role labeling (Collobert et al., 2011). For relation classification and extrac- tion, there are two very recent works on CNNs for relation classification (Liu et al., 2013)2 and (Zeng et al., 2014)."
Understanding representation learned by CNN
Na et al. (2019): Language Concepts in Individual Units of CNNs
- Nguyen, T. H., & Grishman, R. (2015). Relation Extraction : Perspective from Convolutional Neural Networks, 39–48.
- Na, S., Choe, Y. J., Lee, D.-H., & Kim, G. (2019). Discovery of Natural Language Concepts in Individual Units of CNNs. Retrieved from http://arxiv.org/abs/1902.07249