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

Figure 1

The overall architecture of our model. (1) The top left corner shows the input of our model, which is news stream consisting of a lot of news reports. (2) The top right corner shows the shared semantic representation of news stream, which is the input of both event detection network and event evolution network. Note that we utilize a standard bidirectional gated recurrent unit (GRU) model with attention mechanism to learn the shared representation across two subtasks (event detection subtask and event evolution subtask). (3) The bottom right corner shows the event detection module, in which our goal is to aggregate news reports related to the same event together. (4) After detecting a series of events, we further organize these events into multiple stories in an online manner, which forms the event evolution module in the bottom left corner.