MZET: Memory Augmented Zero-Shot Fine-grained Named Entity Typing
This addresses the challenge of handling newly emerged entity types in NLP applications, though it appears incremental as it builds on existing FNET models with memory augmentation.
The paper tackles the problem of zero-shot fine-grained named entity typing for unseen entity types, achieving up to 7% gain in Micro-F1 and Macro-F1 scores over state-of-the-art models.
Named entity typing (NET) is a classification task of assigning an entity mention in the context with given semantic types. However, with the growing size and granularity of the entity types, rare researches in previous concern with newly emerged entity types. In this paper, we propose MZET, a novel memory augmented FNET (Fine-grained NET) model, to tackle the unseen types in a zero-shot manner. MZET incorporates character-level, word-level, and contextural-level information to learn the entity mention representation. Besides, MZET considers the semantic meaning and the hierarchical structure into the entity type representation. Finally, through the memory component which models the relationship between the entity mention and the entity type, MZET transfer the knowledge from seen entity types to the zero-shot ones. Extensive experiments on three public datasets show prominent performance obtained by MZET, which surpasses the state-of-the-art FNET neural network models with up to 7% gain in Micro-F1 and Macro-F1 score.