What kind of model is suitable for this scenery? (deal with synonym)

[guotong1988]

Train data: Who is Michael Jordan? and Who is Air Jordan? are one right match.
The test data is Who is Jumpman Jordan? and Who is Air Jordan?

What feature should I add for training? Which model can capture the match info for this case?

Thank you！！！
@Accagain2014

[Accagain2014]

I think in this case, we should use some semantic model to capture the hidden semantic relation between "Michael Jordan and Air Jordan". Because we can't get any different information in the level of words.