UniHD@CL-SciSumm 2020: Citation Extraction as Search
Dennis Aumiller, Satya Almasian, Philip Hausner, Michael Gertz · 2020
This work presents the entry by the team from Heidelberg University in the CL-SciSumm 2020 shared task at the Scholarly Document Processing workshop at EMNLP 2020.As in its previous iterations, the task is to highlight relevant parts in a reference paper, depending on a citance text excerpt from a citing paper.We participated in tasks 1A (cited text span identification) and 1B (citation context classification).Contrary to most previous works, we frame Task 1A as a search relevance problem, and introduce a 2-step re-ranking approach, which consists of a preselection based on BM25 in addition to positional document features, and a top-k re-ranking with BERT.For Task 1B, we follow previous submissions in applying methods that deal well with low resources and imbalanced classes.