Event2Vec: additive event embeddings where a linear score on a history decomposes exactly into per-event terms [P]

I've been working on Event2Vec, a small library for learning embeddings of discrete event sequences (purchases, logs, clinical codes, etc.) with a deliberately simple structure: a history is the running sum of its event vectors. h_t = h_{t-1} + e_{x_t} (norm-clipped) p(x_{t+1} | h_t) = softmax(W h_t