← Back to all news
arXiv Computation and Language By Jiaxin Duan, Fengyu Lu, Junfei Liu

PiPMRE: A Pipeline Based on Language Model for Medical Relation Extraction

Read the original on arXiv Computation and Language →

PiPMRE is a new pipeline for medical relation extraction that uses language models instead of traditional tagging schemes. The framework includes a relation generator that produces multiple relational triplets from a text and a relation filter that scores and selects the most reliable triplets. Experiments on two public datasets show that PiPMRE outperforms previous state‑of‑the‑art methods, improving recall by 5.6 points and accuracy by 4.4 points, and it also performs well in few‑shot scenarios.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv Computation and Language
Sep 18

Fine-Tuning Models for Biomedical Relation Extraction

The paper introduces pre‑trained models for extracting variant‑phenotype relations from biomedical text, focusing on the SNPPhenA corpus. Fine‑tuning small BERT‑based models, especially DeBERTa, achieves performance close to the current state‑of‑the‑art. Moreover, careful fine‑tuning of Google’s Gemini Pro 1.0 surpasses existing benchmarks on both sentence‑level and abstract‑level relation extraction tasks.

By Claudiu Creanga, Liviu P. Dinu, Daniela Gifu
llmsfine-tuningbenchmarks
More like this →
arXiv Computation and Language
Sep 1

Configurable Semantic Chunking for Biomedical Information Extraction in Retrieval-Augmented Generation

The paper introduces a configurable semantic chunking framework for biomedical information extraction in retrieval‑augmented generation systems. It replaces the fixed‑size chunking stage of BioMedRAG with entity‑preserving windows, trigger‑centered chunking, proposition‑first extraction, tiered trigger prioritization, and hierarchical relation resolution, while keeping the rest of the pipeline unchanged. Experiments on relation extraction benchmarks (GM‑CIHT, DDI, ChemProt) and adverse event classification (ADE) show that the hybrid configuration boosts performance on datasets with explicit relation cues, achieving 82.6% F1 on GM‑CIHT compared to 74.2% with the baseline.

By Riya Ahuja (Institute of Data Science in Biomedicine, TU Braunschweig, Braunschweig, Germany, Braunschweig Integrated Centre of Systems Biology, TU Braunschweig, Braunschweig, Germany), Tim Kacprowski (Institute of Data Science in Biomedicine, TU Braunschweig, Braunschweig, Germany, Braunschweig Integrated Centre of Systems Biology, TU Braunschweig, Braunschweig, Germany), Roya Shiasi Sardoabi (Institute of Data Science in Biomedicine, TU Braunschweig, Braunschweig, Germany, Braunschweig Integrated Centre of Systems Biology, TU Braunschweig, Braunschweig, Germany)
ragbenchmarks
More like this →
arXiv Computation and Language
Sep 16

SciNLP: A Domain-Specific Benchmark for Full-Text Scientific Entity and Relation Extraction in NLP

SciNLP is a new benchmark dataset for full‑text entity and relation extraction in the NLP domain, comprising 60 manually annotated papers with 6,429 entities and 1,649 relations. It is the first dataset to provide full‑text annotations of entities and their relationships specifically for NLP literature. Experiments show that models trained on SciNLP outperform baselines on certain tasks, and the dataset enabled the automatic construction of a fine‑grained knowledge graph with an average node degree of 3.3.

By Decheng Duan, Yingyi Zhang, Jitong Peng, Chengzhi Zhang
nlpbenchmarks
More like this →