An attention-based Bi-GRU-CapsNet model for hypernymy detection between compound entities
This addresses a domain-specific problem in NLP for medical or similar fields, but appears incremental as it combines existing techniques.
The paper tackles hypernymy detection between compound entities by proposing an attention-based Bi-GRU-CapsNet model, achieving experimental results that demonstrate its effectiveness.
Named entities are usually composable and extensible. Typical examples are names of symptoms and diseases in medical areas. To distinguish these entities from general entities, we name them \textit{compound entities}. In this paper, we present an attention-based Bi-GRU-CapsNet model to detect hypernymy relationship between compound entities. Our model consists of several important components. To avoid the out-of-vocabulary problem, English words or Chinese characters in compound entities are fed into the bidirectional gated recurrent units. An attention mechanism is designed to focus on the differences between the two compound entities. Since there are some different cases in hypernymy relationship between compound entities, capsule network is finally employed to decide whether the hypernymy relationship exists or not. Experimental results demonstrate