Dataset

LectureBank-Full Prerequisite QA Benchmark

LectureBank-Full is the expanded configuration of the LectureBank corpus used as a prerequisite-QA / retrieval benchmark. It contains 1,7171{,}717 English NLP-related lecture slide files and manual concept-pair prerequisite annotations over 322322 topics. The task is to retrieve, for a given target concept (query), the set of gold prerequisite concepts from a fixed candidate pool. Systems are scored with ranking metrics such as Recall@kk (R@kk); R@1010 measures the fraction of gold prerequisites recovered in the top-1010 retrieved candidates. Standard splits hold out concept pairs for evaluation, and headline comparisons fix the encoder, candidate pool, cutoff, matching rule, and split policy.

0

1

Updated 2026-05-18

Contributors are:

Who are from:

Tags

Science