I’m doing research on natural language processing (NLP). I’d like to put together my own model. However, I'm running into a concept I am not familiar with, namely, distractors. A google search does not reveal much.
I've been reading this article specifically: https://medium.com/huggingface/how-to-build-a-state-of-the-art-conversational-ai-with-transfer-learning-2d818ac26313
In the section under "Multi-Tasks Losses" it reads:
Next-sentence prediction: we pass the hidden-state of the last token (the end-of-sequence token) through a linear layer to get a score and apply a cross-entropy loss to classify correctly a gold answer among distractors.
I understand how transformers and coss-entropy works, however I'm not sure what a distractor or a "gold answer" is for that matter.
In this context, what does the author mean by distractor?