Extracting Biographical Spatial Timelines: Corpus and Experiments
Alakananda Vempala, Eduardo Blanco · IEEE/ACM Transactions on Audio Speech and Language Processing · 2020
This article presents a corpus and experiments to extract spatial timelines from biographies. Spatial timelines capture where someone is and is not located, and specify when this spatial information is true. We work with 100 Wikipedia biographies, and consider intersentential (location, year) pairs as well as years that are not explicitly stated in the biographies. Experimental results show that a combination of LSTMs outperforms SVM with linguistically motivated features.