Robust triple extraction with cascade bidirectional capsule network.

Recent approaches have witnessed the success of neural models for triple extraction. However, we empirically observe that previous approaches may fail for those disambiguate text expressed in a similar context and generate triples that contradict the commonsense. Such issues severely hinder the generalization of triple extraction in real-world applications. Motivated by the capsule networks' power of modeling latent structures and the implicit entity-relation schema, we propose a novel Cascade Bidirectional Capsule Network (CBCapsule) to address those issues. We firstly introduce a cascade capsule network to dynamically aggregate context representations and then propose a bidirectional routing mechanism to encourage interaction between the high level (e.g., relations) and low level (e.g., entities) capsules. Experimental results on three benchmarks show that our proposed approach is more efficient than baselines and has a more robust generalization ability with complex surface forms. • The first model using capsule network in triple extraction. • Modeling the parts-wholes between entities and relations. • A robust model for triple extraction with diverse surface forms. • Can handle overlapping relational triples. • Good performance in benchmarks and obtain better results in robust settings. [ABSTRACT FROM AUTHOR]