Table 2 Proposed algorithm of active learning with TEES

// Initialization

E R ₀ = the set of events/relations annotated on L

Learn a TEES model M ₀ from E R ₀

i = 0 // the index of the current round

// Active Learning Loop

while U is not empty:

i += 1

for each document D _{i j} in U:

Document informativity score I(D _{i j} )=0

for each sentence S _k in D _{i j} :

Apply M _i−1 to S _k and collect the resultant events/relations set \(ER_{S_{k}}\)

for each event/relation er s.t. er \(\notin ER_{s_k}\):

I(D _{i j} ) += informativity score I(S _k ,e r)

I(D _{i j} ) = I(D _{i j} ) / sizeOf(D _{i j} )

Rank D _{i j} in U based on I(D _{i j} ) and select the top b documents,

designated as B

Remove B from U, add B to L, and add the annotations on B to E R _i−1,

designated as E R _i

Learn a new model M _i from E R _i