Giters

seominjoon / denspi

Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index (DenSPI)

Home Page:https://nlp.cs.washington.edu/denspi

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

neg training code is different from the paper

seominjoon opened this issue · comments

commented

Currently the neg training routine (--train_neg in run_piqa.py) is different from what is described in the paper.

In the paper, we use 'no answer' logit to train on negative examples so we just don't have a separate neg training routine. In the code, we have a neg training routine that instead attaches the neg example to each positive example (whose question embeddings are similar) after normal training.

In the code, several noise injections are also used.

In practice, the strategy in the current code is better than that in the paper (no answer logit). The paper will be updated soon and this issue will be resolved.