@inproceedings{barteld-etal-2026-joint,
title = "Joint Identification and Induction of Semantic Frames with Scalable Semi-Supervised Graph Clustering",
author = "Barteld, Fabian and
Remus, Steffen and
Anwar, Saba and
Stawecki, Julian and
Ziem, Alexander and
Biemann, Chris",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.786/",
doi = "10.63317/5q7o3fgim7pb",
pages = "10020--10030",
abstract = "Current methods for automatically assigning frames to their evoking words can be divided into frame identification and frame induction. In frame identification, frame names coming from a labeled dataset are assigned to unseen instances, a classical supervised labeling task. However, the training datasets are known to be incomplete in terms of real-world frames, resulting in an issue with potentially new frame labels. In frame induction, instances are clustered regarding the frames they evoke, a classical unsupervised clustering task. However, existing training data is not used to identify known frames. To overcome these shortcomings, we propose to use semi-supervised clustering for combined frame identification and frame induction. By using constrained clustering with hard constraints coming from labeled data, the resulting clusters contain only labeled instances with the same label. Thus, frame names can be easily assigned. We show for English and German datasets that using semi-supervised clustering improves the quality of frame induction compared to unsupervised clustering methods and results in notably good performance regarding frame identification."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="barteld-etal-2026-joint">
<titleInfo>
<title>Joint Identification and Induction of Semantic Frames with Scalable Semi-Supervised Graph Clustering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fabian</namePart>
<namePart type="family">Barteld</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steffen</namePart>
<namePart type="family">Remus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saba</namePart>
<namePart type="family">Anwar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julian</namePart>
<namePart type="family">Stawecki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Ziem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Biemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Current methods for automatically assigning frames to their evoking words can be divided into frame identification and frame induction. In frame identification, frame names coming from a labeled dataset are assigned to unseen instances, a classical supervised labeling task. However, the training datasets are known to be incomplete in terms of real-world frames, resulting in an issue with potentially new frame labels. In frame induction, instances are clustered regarding the frames they evoke, a classical unsupervised clustering task. However, existing training data is not used to identify known frames. To overcome these shortcomings, we propose to use semi-supervised clustering for combined frame identification and frame induction. By using constrained clustering with hard constraints coming from labeled data, the resulting clusters contain only labeled instances with the same label. Thus, frame names can be easily assigned. We show for English and German datasets that using semi-supervised clustering improves the quality of frame induction compared to unsupervised clustering methods and results in notably good performance regarding frame identification.</abstract>
<identifier type="citekey">barteld-etal-2026-joint</identifier>
<identifier type="doi">10.63317/5q7o3fgim7pb</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.786/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>10020</start>
<end>10030</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Joint Identification and Induction of Semantic Frames with Scalable Semi-Supervised Graph Clustering
%A Barteld, Fabian
%A Remus, Steffen
%A Anwar, Saba
%A Stawecki, Julian
%A Ziem, Alexander
%A Biemann, Chris
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F barteld-etal-2026-joint
%X Current methods for automatically assigning frames to their evoking words can be divided into frame identification and frame induction. In frame identification, frame names coming from a labeled dataset are assigned to unseen instances, a classical supervised labeling task. However, the training datasets are known to be incomplete in terms of real-world frames, resulting in an issue with potentially new frame labels. In frame induction, instances are clustered regarding the frames they evoke, a classical unsupervised clustering task. However, existing training data is not used to identify known frames. To overcome these shortcomings, we propose to use semi-supervised clustering for combined frame identification and frame induction. By using constrained clustering with hard constraints coming from labeled data, the resulting clusters contain only labeled instances with the same label. Thus, frame names can be easily assigned. We show for English and German datasets that using semi-supervised clustering improves the quality of frame induction compared to unsupervised clustering methods and results in notably good performance regarding frame identification.
%R 10.63317/5q7o3fgim7pb
%U https://aclanthology.org/2026.lrec-1.786/
%U https://doi.org/10.63317/5q7o3fgim7pb
%P 10020-10030
Markdown (Informal)
[Joint Identification and Induction of Semantic Frames with Scalable Semi-Supervised Graph Clustering](https://aclanthology.org/2026.lrec-1.786/) (Barteld et al., LREC 2026)
ACL