A Hybrid Model of Classification and Generation for Spatial Relation Extraction
This work addresses a fundamental natural language understanding problem for applications like robotics or GIS by improving extraction accuracy, though it is incremental as it builds on existing classification approaches.
The paper tackles spatial relation extraction by proposing a hybrid model that combines classification and generation to handle both null-role and non-null-role relations, achieving significant performance improvements over state-of-the-art baselines on the SpaceEval dataset.
Extracting spatial relations from texts is a fundamental task for natural language understanding and previous studies only regard it as a classification task, ignoring those spatial relations with null roles due to their poor information. To address the above issue, we first view spatial relation extraction as a generation task and propose a novel hybrid model HMCGR for this task. HMCGR contains a generation and a classification model, while the former can generate those null-role relations and the latter can extract those non-null-role relations to complement each other. Moreover, a reflexivity evaluation mechanism is applied to further improve the accuracy based on the reflexivity principle of spatial relation. Experimental results on SpaceEval show that HMCGR outperforms the SOTA baselines significantly.