@inproceedings{kawarada-etal-2026-structure,
title = "Structure-Aware Data Augmentation for Argument Mining",
author = "Kawarada, Masayuki and
Hirao, Tsutomu and
Okumura, Manabu",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.98/",
pages = "2295--2310",
ISBN = "979-8-89176-459-0",
abstract = "This paper introduces a novel data augmentation approach designed for argument mining. Argument mining is a task that automatically identifies argumentative structures within texts, typically represented as trees or directed acyclic graphs (DAGs). A major challenge facing current argument mining systems is the limited structural diversity of existing annotated datasets, as manual annotation inevitably captures only a small subset of the argumentative patterns encountered in practice. To overcome this challenge, we propose an innovative data augmentation method. Our approach begins by generating pseudo-argumentative structures through the exploration of various combinations of argument labels. These structures then guide a large language model (LLM) to produce new texts with annotations directly incorporated into the text. We evaluated our method on the Argument Annotated Essay Corpus (AAEC) and the AbstRCT dataset. Experimental results showed that the proposed method outperformed existing augmentation baselines on Component-F1 and Relation-F1 in most settings. Further analysis indicated that the variety in the generated pseudo-argumentative structures plays a crucial role in achieving these improvements."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kawarada-etal-2026-structure">
<titleInfo>
<title>Structure-Aware Data Augmentation for Argument Mining</title>
</titleInfo>
<name type="personal">
<namePart type="given">Masayuki</namePart>
<namePart type="family">Kawarada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tsutomu</namePart>
<namePart type="family">Hirao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manabu</namePart>
<namePart type="family">Okumura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>This paper introduces a novel data augmentation approach designed for argument mining. Argument mining is a task that automatically identifies argumentative structures within texts, typically represented as trees or directed acyclic graphs (DAGs). A major challenge facing current argument mining systems is the limited structural diversity of existing annotated datasets, as manual annotation inevitably captures only a small subset of the argumentative patterns encountered in practice. To overcome this challenge, we propose an innovative data augmentation method. Our approach begins by generating pseudo-argumentative structures through the exploration of various combinations of argument labels. These structures then guide a large language model (LLM) to produce new texts with annotations directly incorporated into the text. We evaluated our method on the Argument Annotated Essay Corpus (AAEC) and the AbstRCT dataset. Experimental results showed that the proposed method outperformed existing augmentation baselines on Component-F1 and Relation-F1 in most settings. Further analysis indicated that the variety in the generated pseudo-argumentative structures plays a crucial role in achieving these improvements.</abstract>
<identifier type="citekey">kawarada-etal-2026-structure</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.98/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>2295</start>
<end>2310</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Structure-Aware Data Augmentation for Argument Mining
%A Kawarada, Masayuki
%A Hirao, Tsutomu
%A Okumura, Manabu
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F kawarada-etal-2026-structure
%X This paper introduces a novel data augmentation approach designed for argument mining. Argument mining is a task that automatically identifies argumentative structures within texts, typically represented as trees or directed acyclic graphs (DAGs). A major challenge facing current argument mining systems is the limited structural diversity of existing annotated datasets, as manual annotation inevitably captures only a small subset of the argumentative patterns encountered in practice. To overcome this challenge, we propose an innovative data augmentation method. Our approach begins by generating pseudo-argumentative structures through the exploration of various combinations of argument labels. These structures then guide a large language model (LLM) to produce new texts with annotations directly incorporated into the text. We evaluated our method on the Argument Annotated Essay Corpus (AAEC) and the AbstRCT dataset. Experimental results showed that the proposed method outperformed existing augmentation baselines on Component-F1 and Relation-F1 in most settings. Further analysis indicated that the variety in the generated pseudo-argumentative structures plays a crucial role in achieving these improvements.
%U https://aclanthology.org/2026.emnlp-main.98/
%P 2295-2310
Markdown (Informal)
[Structure-Aware Data Augmentation for Argument Mining](https://aclanthology.org/2026.emnlp-main.98/) (Kawarada et al., EMNLP 2026)
ACL
- Masayuki Kawarada, Tsutomu Hirao, and Manabu Okumura. 2026. Structure-Aware Data Augmentation for Argument Mining. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 2295–2310, Budapest, Hungary. Association for Computational Linguistics.