@inproceedings{winkle-etal-2026-generative-information,
title = "Generative Information Extraction from Biographical Sources",
author = {Winkle, Robin and
Stede, Manfred and
Kreutel, J{\"o}rn},
editor = "Alves, Diego and
Bizzoni, Yuri and
Degaetano-Ortlieb, Stefania and
Kazantseva, Anna and
Pagel, Janis and
Szpakowicz, Stan",
booktitle = "Proceedings of the 10th Joint {SIGHUM} Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature 2026",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.latechclfl-1.30/",
pages = "311--322",
ISBN = "979-8-89176-373-9",
abstract = "Biographical sources, such as literature encyclopedias, encode knowledge about historical figures in textual form. In this paper, we address the task of consolidating structured biographical information about authors from the former German Democratic Republic into a unified database. To this end, we present a generalizable Information Extraction (IE) system based on LLM prompting. Specifically, we compare two midsized open-source models, Qwen-2.5-32B and Llama-3-70B-Instruct, investigate a range of Prompt Engineering (PE) strategies, and propose a semantic similarity-based evaluation metric for open-ended IE. Our experiments on an unpublished annotated subset of biographical texts deliver moderate precision and variable recall, highlighting both the potential and current limitations of generative IE in the Digital Humanities."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="winkle-etal-2026-generative-information">
<titleInfo>
<title>Generative Information Extraction from Biographical Sources</title>
</titleInfo>
<name type="personal">
<namePart type="given">Robin</namePart>
<namePart type="family">Winkle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manfred</namePart>
<namePart type="family">Stede</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörn</namePart>
<namePart type="family">Kreutel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Diego</namePart>
<namePart type="family">Alves</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuri</namePart>
<namePart type="family">Bizzoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefania</namePart>
<namePart type="family">Degaetano-Ortlieb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Kazantseva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Janis</namePart>
<namePart type="family">Pagel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stan</namePart>
<namePart type="family">Szpakowicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-373-9</identifier>
</relatedItem>
<abstract>Biographical sources, such as literature encyclopedias, encode knowledge about historical figures in textual form. In this paper, we address the task of consolidating structured biographical information about authors from the former German Democratic Republic into a unified database. To this end, we present a generalizable Information Extraction (IE) system based on LLM prompting. Specifically, we compare two midsized open-source models, Qwen-2.5-32B and Llama-3-70B-Instruct, investigate a range of Prompt Engineering (PE) strategies, and propose a semantic similarity-based evaluation metric for open-ended IE. Our experiments on an unpublished annotated subset of biographical texts deliver moderate precision and variable recall, highlighting both the potential and current limitations of generative IE in the Digital Humanities.</abstract>
<identifier type="citekey">winkle-etal-2026-generative-information</identifier>
<location>
<url>https://aclanthology.org/2026.latechclfl-1.30/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>311</start>
<end>322</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generative Information Extraction from Biographical Sources
%A Winkle, Robin
%A Stede, Manfred
%A Kreutel, Jörn
%Y Alves, Diego
%Y Bizzoni, Yuri
%Y Degaetano-Ortlieb, Stefania
%Y Kazantseva, Anna
%Y Pagel, Janis
%Y Szpakowicz, Stan
%S Proceedings of the 10th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature 2026
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-373-9
%F winkle-etal-2026-generative-information
%X Biographical sources, such as literature encyclopedias, encode knowledge about historical figures in textual form. In this paper, we address the task of consolidating structured biographical information about authors from the former German Democratic Republic into a unified database. To this end, we present a generalizable Information Extraction (IE) system based on LLM prompting. Specifically, we compare two midsized open-source models, Qwen-2.5-32B and Llama-3-70B-Instruct, investigate a range of Prompt Engineering (PE) strategies, and propose a semantic similarity-based evaluation metric for open-ended IE. Our experiments on an unpublished annotated subset of biographical texts deliver moderate precision and variable recall, highlighting both the potential and current limitations of generative IE in the Digital Humanities.
%U https://aclanthology.org/2026.latechclfl-1.30/
%P 311-322
Markdown (Informal)
[Generative Information Extraction from Biographical Sources](https://aclanthology.org/2026.latechclfl-1.30/) (Winkle et al., LaTeCH-CLfL 2026)
ACL
- Robin Winkle, Manfred Stede, and Jörn Kreutel. 2026. Generative Information Extraction from Biographical Sources. In Proceedings of the 10th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature 2026, pages 311–322, Rabat, Morocco. Association for Computational Linguistics.