search

openai / deeptype

Code for the paper "DeepType: Multilingual Entity Linking by Neural Type System Evolution"
https://arxiv.org/abs/1802.01021
Other
649 stars 146 forks source link

the paper is hard to understand #24

Closed herbertchen1 closed 6 years ago

herbertchen1 commented 6 years ago

In the last of the section 3, i find the scoring function S(e,m,D,A,θ) ,argmax it to get the optimal entity.

however ,the formulation seems have no relation with the candidate entity, it's just Plink(e,m) mutiply a constant given a single mention. I don't know whether i have a bad understanding of the paper，or maybe Pi,（m） need to multiply a deterministic Pi,（e） which is got from the wikidata? sincerely hope for your answer.

JonathanRaiman commented 6 years ago

Thanks you for bringing this up. Hopefully the following clarifies this point.

I believe you are referring to equation (6), where the scoring function is defined. In this case P_i (t_i, m, D) is a function that estimates the likelihood of mention m from document D belonging to type t_i. Each entity has a set of associated types that defines it (so Types(e) = {t_1, ..., t_k}), hence t_i is actually a property of e (apologies for omission of the subscript e in t_i). The paragraph above introduces t_i. Hope this helps!

herbertchen1 commented 6 years ago

Thanks for your answer！！！