Graph-based Syntactic Word Embeddings
Conference article in proceedings
Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs)
AbstractWe propose a simple and efficient framework to learn syntactic embeddings based on information derived from constituency parse trees. Using biased random walk methods, our embeddings not only encode syntactic information about words, but they also capture contextual information. We also propose a method to train the embeddings on multiple constituency parse trees to ensure the encoding of global syntactic representation. Quantitative evaluation of the embeddings shows competitive performance on POS tagging task when compared to other types of embeddings, and qualitative evaluation reveals interesting facts about the syntactic typology learned by these embeddings.
Al-Ghezi , R & Kurimo , M 2020 , Graph-based Syntactic Word Embeddings . in Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs) . Association for Computational Linguistics , pp. 72–78 , Workshop on Graph-Based Methods for Natural Language Processing , Barcelona , Spain , 13/12/2020 . < https://www.aclweb.org/anthology/2020.textgraphs-1.8/ >