Diversified Semantic Attention Model for Fine-Grained Entity Typing
Yanfeng Hu, Xue Qiao, Xing Luo, Peng Chen · IEEE Access · 2020
Fine-grained entity typing, which aims to assign specific types to entity mentions in text, is attracting increasing attention in the field of natural language processing (NLP). However, it is quite a challenging problem due to the highly ambiguous nature of many entity mentions. Most existing entity typing methods based on attention mechanism generally extract the salient features separately from the entity mention and the contextual words. However, these approaches suffer fromtwo main limitations: (1) They ignore the rich information contained by entity mentions when applying the attention mechanisms. (2) They do not consider the diversity of attention processes which can be beneficial in finding the discriminative features. To address these issues, we propose thediversified semantic attention model (DSAM)for fine-grained entity typing, and the main novelties are: (1) It explicitly pursues the diversity of attention and is able to maximally gather discriminative information. (2) It integrates two level attentions—themention-level attentionand thecontext-level attention—to jointly capture the rich information from mentions and contexts to enhance their mutual promotions. (3) It combines theattention maps constraintand theattention segments constrainto exploit the subtle semantic differences for distinguishing the subtypes. Importantly, the proposed DSAM approach can be trained end-to-end without employing ad-hoc features or post-processing. Extensive experiments using three benchmark datasets demonstrated that our DSAM approach achieves competitive performance compared to the current state-of-the-art methods used for fine-grained entity typing.