SciNLP is the first full-text entity and relation extraction benchmark for the NLP domain, built from 60 manually annotated publications and used to evaluate models and construct a domain knowledge graph.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
ECHO reframes multimedia event extraction as multi-agent iterative refinement over an explicit Multimedia Event Hypergraph with a decoupled Link-then-Bind strategy, delivering 7.3 and 15.5 F1 gains on event mention and argument role.
citing papers explorer
-
SciNLP: A Domain-Specific Benchmark for Full-Text Scientific Entity and Relation Extraction in NLP
SciNLP is the first full-text entity and relation extraction benchmark for the NLP domain, built from 60 manually annotated publications and used to evaluate models and construct a domain knowledge graph.
-
ECHO: Event-Centric Hypergraph Operations via Multi-Agent Collaboration for Multimedia Event Extraction
ECHO reframes multimedia event extraction as multi-agent iterative refinement over an explicit Multimedia Event Hypergraph with a decoupled Link-then-Bind strategy, delivering 7.3 and 15.5 F1 gains on event mention and argument role.