Compositional embedding models build a representation for a linguistic structure based on its component word embeddings. While recent work has combined these word embeddings with hand crafted features for improved performance, it was restricted to a small number of features due to model complexity, thus limiting its applicability. We propose a new model that conjoins features and word embeddings while maintaing a small number of parameters by learning feature embeddings jointly with the parameters of a compositional model. The result is a method that can scale to more features and more labels, while avoiding overfitting. We demonstrate that our model attains state-of-the-art results on ACE and ERE fine-grained relation extraction.
CITATION STYLE
Yu, M., Gormley, M. R., & Dredze, M. (2015). Combining word embeddings and feature embeddings for fine-grained relation extraction. In NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference (pp. 1374–1379). Association for Computational Linguistics (ACL). https://doi.org/10.3115/v1/n15-1155
Mendeley helps you to discover research relevant for your work.