Texts have become an essential spatial data resource in recent years. One leading task to manage the texts’ conveyed spatial data is the Spatial role labeling (SpRL). The latter intends the extraction of formal spatial knowledge from text. Instead of treating the text as a straightforward sequence of words, we incorporate syntactic dependencies to identify entities uttering spatial semantics. First, we investigate the impact of dependency-based word embeddings in SpRL. Then, we propose a dependency-guided LSTM-CRF deep learning model to exploit syntactic relationships among words. Then, we enhance these dependencies features with POS tags and CNN-based character-level representations. Experiments are performed on the standard SpRL-2012 and SpRL-2013 datasets. The experimental results show that the proposed model outperforms other machine learning approaches. The findings show the importance of taking dependencies into account in SpRL tasks.
Moussa et al. (Sat,) studied this question.