Closed ShellingFord221 closed 3 years ago
Are 2487 and 2475 just the IDs of symbol '<e1'> and '<e2'>?
As we pointed out in the paper, we use [E1] and [E2] to represent two entities, and 2487 and 2475 mean the IDs corresponding to [E1] and [E2] in the BERT Tokenizer.
So there is no vocabulary for entity's mention? Just the indicator [E1] and [E2] for entities in all sentences?
Yes, since BERT could encode contextualized relational features, [E1] and [E2] could be used to represent entity-level relational features. A similar approach can also be found in our reference paper Figure 3.
Got it. Thx.
Hi, in
train.py
, you find entity's position by:What do 2487 and 2475 mean? If an entity is composed of multiple words (e.g. Gossip Girl), how do you get this entity's encoding? Thanks!