Search code examples
stanford-nlp

What is the purpose of EventMention in Stanford-NLP?


When using the pipeline annotator, relation, I get back appropriate RelationMention objects for each sentence. These are binary type objects with two entity mentions and a corresponding relation type.

However, in the code, I also see EventMention objects which can be obtained from the sentence in much the same way. In the class MachineReadingProperties, I see that extraction of relations and extraction of events both default to true. However, I am only seeing generated relations and not generated events.

I can find no mention of events in the Stanford documentation, nor does the page describing the relation annotator or how to train a custom relation model describe it. There are no links to research papers on the event portion, just the link to the Roth and Yih paper on relations.

So do events work with the relation annotator and if so are there any more documents describing them?


Solution

  • From tracing the code, I see that EventMention is only used in conjunction with the ACE2005 code. It does not appear to be connected with any of the pipeline annotators and cannot be directly created in that manner.