Saved in:
Bibliographic Details
Main Author: Solaiman, KMA
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.03949
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918083687350272
author Solaiman, KMA
author_facet Solaiman, KMA
contents We propose POSID, a modular, lightweight and on-demand framework for extracting structured attribute-based properties from unstructured text without task-specific fine-tuning. While the method is designed to be adaptable across domains, in this work, we evaluate it on human attribute recognition in incident reports. POSID combines lexical and semantic similarity techniques to identify relevant sentences and extract attributes. We demonstrate its effectiveness on a missing person use case using the InciText dataset, achieving effective attribute extraction without supervised training.
format Preprint
id arxiv_https___arxiv_org_abs_2507_03949
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Modular Unsupervised Framework for Attribute Recognition from Unstructured Text
Solaiman, KMA
Computation and Language
We propose POSID, a modular, lightweight and on-demand framework for extracting structured attribute-based properties from unstructured text without task-specific fine-tuning. While the method is designed to be adaptable across domains, in this work, we evaluate it on human attribute recognition in incident reports. POSID combines lexical and semantic similarity techniques to identify relevant sentences and extract attributes. We demonstrate its effectiveness on a missing person use case using the InciText dataset, achieving effective attribute extraction without supervised training.
title A Modular Unsupervised Framework for Attribute Recognition from Unstructured Text
topic Computation and Language
url https://arxiv.org/abs/2507.03949