Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction
read the original abstract
We introduce a multi-task setup of identifying and classifying entities, relations, and coreference clusters in scientific articles. We create SciERC, a dataset that includes annotations for all three tasks and develop a unified framework called Scientific Information Extractor (SciIE) for with shared span representations. The multi-task setup reduces cascading errors between tasks and leverages cross-sentence relations through coreference links. Experiments show that our multi-task model outperforms previous models in scientific information extraction without using any domain-specific features. We further show that the framework supports construction of a scientific knowledge graph, which we use to analyze information in scientific literature.
This paper has not been read by Pith yet.
Forward citations
Cited by 3 Pith papers
-
CHIMERA: A Knowledge Base of Scientific Idea Recombinations for Research Analysis and Ideation
CHIMERA is the first large-scale mined KB of concept recombinations from scientific literature, created via a new IE task and LLM extraction, with demonstrated uses in pattern analysis and hypothesis generation.
-
MeasHalu: Mitigation of Scientific Measurement Hallucinations for Large Language Models with Enhanced Reasoning
MeasHalu reduces LLM hallucinations in scientific measurement extraction via a fine-grained taxonomy, reasoning-aware fine-tuning, and progressive rewards, improving accuracy on the MeasEval benchmark.
-
Capturing Monetarily Exploitable Vulnerability in Smart Contracts via Auditor Knowledge-Learning Fuzzing
FAUDITOR is a specialized fuzzer that detected 220 zero-day monetarily exploitable vulnerabilities in smart contracts by combining finance-interface targeting, NLP from auditor reports, and self-learning.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.