English

Slot Filling for Biomedical Information Extraction

Computation and Language 2022-04-12 v2 Information Retrieval Machine Learning

Abstract

Information Extraction (IE) from text refers to the task of extracting structured knowledge from unstructured text. The task typically consists of a series of sub-tasks such as Named Entity Recognition and Relation Extraction. Sourcing entity and relation type specific training data is a major bottleneck in domains with limited resources such as biomedicine. In this work we present a slot filling approach to the task of biomedical IE, effectively replacing the need for entity and relation-specific training data, allowing us to deal with zero-shot settings. We follow the recently proposed paradigm of coupling a Tranformer-based bi-encoder, Dense Passage Retrieval, with a Transformer-based reading comprehension model to extract relations from biomedical text. We assemble a biomedical slot filling dataset for both retrieval and reading comprehension and conduct a series of experiments demonstrating that our approach outperforms a number of simpler baselines. We also evaluate our approach end-to-end for standard as well as zero-shot settings. Our work provides a fresh perspective on how to solve biomedical IE tasks, in the absence of relevant training data. Our code, models and datasets are available at https://github.com/ypapanik/biomedical-slot-filling.

Keywords

Cite

@article{arxiv.2109.08564,
  title  = {Slot Filling for Biomedical Information Extraction},
  author = {Yannis Papanikolaou and Marlene Staib and Justin Grace and Francine Bennett},
  journal= {arXiv preprint arXiv:2109.08564},
  year   = {2022}
}
R2 v1 2026-06-24T06:04:35.643Z