Position feature embedding seems not right?

[peidaqi]

In the paper, it says:

The position should be calculated for each word in the sentence, relative to the two target entity words.
An example was given in the paper:

People have been moving back into downtown

The correspondent embedding for "moving", regarding to "people" and "downtown" should be:
[WordVec, 3, -3]

However, in the code:

What's used is the position of the two entity words. This kinda misses the point of using position embedding as it's supposed to be a means to extract structure features from the sentence.

[FrankWork]

position feature in code is correct.

conv_relation/src/reader/base.py

Line 202 in c1384e5

position1, position2 = _position_feature(raw_example)