The reviewed record of science sign in
Pith

arxiv: 2104.08809 · v3 · pith:B6U2QKD4 · submitted 2021-04-18 · cs.CL · cs.IR· cs.LG

SciCo: Hierarchical Cross-Document Coreference for Scientific Concepts

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:B6U2QKD4record.jsonopen to challenge →

classification cs.CL cs.IRcs.LG
keywords coreferencecdcrconceptsh-cdcrhierarchicalchallengescross-documentmentions
0
0 comments X
read the original abstract

Determining coreference of concept mentions across multiple documents is a fundamental task in natural language understanding. Previous work on cross-document coreference resolution (CDCR) typically considers mentions of events in the news, which seldom involve abstract technical concepts that are prevalent in science and technology. These complex concepts take diverse or ambiguous forms and have many hierarchical levels of granularity (e.g., tasks and subtasks), posing challenges for CDCR. We present a new task of Hierarchical CDCR (H-CDCR) with the goal of jointly inferring coreference clusters and hierarchy between them. We create SciCo, an expert-annotated dataset for H-CDCR in scientific papers, 3X larger than the prominent ECB+ resource. We study strong baseline models that we customize for H-CDCR, and highlight challenges for future work.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.