Table 5.

The performance of the Attention-based model on the test dataset at intra-sentence level

Methods	P(%)	R(%)	F(%)
Intra_HRNN (Baseline)	62.0	55.2	58.4
Intra-Attention	62.2	59.5	60.8
- Descriptor Embedding	61.1	54.2	57.5
- Hyponym Embedding	61.7	56.6	59.0
- Location Embedding	61.9	56.7	59.2
- Entity Difference Embedding	62.1	56.9	59.4