Continuous Similarity Learning with Shared Neural Semantic Representation for Joint Event Detection and Evolution

<div>Illustration of our JEDE model. JEDE consists of two submodels: event detection network and event evolution network. They are based on the shared semantic representation and additional temporal information. The submodels are stacked to enable information sharing between the two tasks.</div>

Computational Intelligence and Neuroscience

fig2

Figure 2

Figure 2: Continuous Similarity Learning with Shared Neural Semantic Representation for Joint Event Detection and Evolution 