PulseAugur
EN
LIVE 22:12:24

New dataset and LLM pipeline extract empirical relations from psychology abstracts

Researchers have developed EmpiriGraph-Psy, a new dataset and pipeline designed to extract empirical relation graphs from psychology abstracts. This system addresses a gap in existing benchmarks, which primarily focus on computer science domains, by enabling the extraction of relationships between constructs, measurements, and outcomes in variable-oriented fields. The pipeline, which separates variable extraction, normalization, and relation identification, significantly outperforms direct extraction methods, achieving a macro-F1 score of 0.74. AI

IMPACT Enables more sophisticated knowledge extraction from scientific literature, potentially accelerating research in psychology and related fields.

RANK_REASON The cluster describes a new academic paper introducing a dataset and methodology for relation extraction in a specific scientific domain.

Read on Hugging Face Daily Papers →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

COVERAGE [2]

  1. arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Thomas T. Hills ·

    EmpiriGraph-Psy: A Dataset and LLM Pipeline for Extracting Empirical Relation Graphs from Psychology Abstracts

    Existing scientific relation extraction benchmarks mainly target domains such as computer science, where entities are tasks, methods, datasets, materials, or metrics. This leaves a gap in variable-oriented empirical fields such as psychology, where findings are expressed as relat…

  2. Hugging Face Daily Papers TIER_1 English(EN) ·

    EmpiriGraph-Psy: A Dataset and LLM Pipeline for Extracting Empirical Relation Graphs from Psychology Abstracts

    Variable-centered empirical graph extraction maps psychology abstracts to typed graphs with normalized variables and empirical relations, achieving improved performance through staged pipeline approaches.