@inproceedings{gurushankar-saisudha-bergler-2026-modeling,
title = "Modeling Perspectives in {NLP}: Parameter-Efficient Perspective Conditioning for Span Extraction and Summarization",
author = "Gurushankar Saisudha, Harikrishnan and
Bergler, Sabine",
editor = "Dudy, Shiran and
Abercrombie, Gavin and
Basile, Valerio and
Leonardelli, Elisa and
Frenda, Simona",
booktitle = "Proceedings of the the fifth edition of {NLP}erspectives",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.nlperspectives-1.12/",
doi = "10.63317/5oecmktyh8bf",
pages = "124--135",
abstract = "Understanding text through multiple perspectives is essential in domains such as healthcare community question answering, where answers frequently contain heterogeneous viewpoints, including experiences, suggestions, causes, follow-up questions, and informational claims. We present a unified perspective-conditioned framework for both span identification and perspective-aware summarization on the PerAnsSumm dataset. Our approach introduces explicit perspective signals into transformer models using two parameter-efficient mechanisms: prefix-conditioned representations and perspective-aware attention layers. We first employ multi-label perspective classification to identify relevant viewpoints, which serve as conditioning signals for downstream tasks. For span identification, we model perspective-specific extraction as a conditioned binary sequence labeling problem. For summarization, we guide generation using perspective-enriched encoder representations. Experiments demonstrate that explicit perspective conditioning substantially improves span detection performance while achieving competitive summarization quality. Notably, perspective-aware attention achieves strong results using only a small fraction of the trainable parameters required by full fine-tuning. Our findings highlight the importance of structured viewpoint modeling and show that explicit perspective control enables efficient and interpretable multi-perspective text understanding."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gurushankar-saisudha-bergler-2026-modeling">
<titleInfo>
<title>Modeling Perspectives in NLP: Parameter-Efficient Perspective Conditioning for Span Extraction and Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Harikrishnan</namePart>
<namePart type="family">Gurushankar Saisudha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabine</namePart>
<namePart type="family">Bergler</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 the fifth edition of NLPerspectives</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shiran</namePart>
<namePart type="family">Dudy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gavin</namePart>
<namePart type="family">Abercrombie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valerio</namePart>
<namePart type="family">Basile</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="family">Leonardelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simona</namePart>
<namePart type="family">Frenda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Understanding text through multiple perspectives is essential in domains such as healthcare community question answering, where answers frequently contain heterogeneous viewpoints, including experiences, suggestions, causes, follow-up questions, and informational claims. We present a unified perspective-conditioned framework for both span identification and perspective-aware summarization on the PerAnsSumm dataset. Our approach introduces explicit perspective signals into transformer models using two parameter-efficient mechanisms: prefix-conditioned representations and perspective-aware attention layers. We first employ multi-label perspective classification to identify relevant viewpoints, which serve as conditioning signals for downstream tasks. For span identification, we model perspective-specific extraction as a conditioned binary sequence labeling problem. For summarization, we guide generation using perspective-enriched encoder representations. Experiments demonstrate that explicit perspective conditioning substantially improves span detection performance while achieving competitive summarization quality. Notably, perspective-aware attention achieves strong results using only a small fraction of the trainable parameters required by full fine-tuning. Our findings highlight the importance of structured viewpoint modeling and show that explicit perspective control enables efficient and interpretable multi-perspective text understanding.</abstract>
<identifier type="citekey">gurushankar-saisudha-bergler-2026-modeling</identifier>
<identifier type="doi">10.63317/5oecmktyh8bf</identifier>
<location>
<url>https://aclanthology.org/2026.nlperspectives-1.12/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>124</start>
<end>135</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Modeling Perspectives in NLP: Parameter-Efficient Perspective Conditioning for Span Extraction and Summarization
%A Gurushankar Saisudha, Harikrishnan
%A Bergler, Sabine
%Y Dudy, Shiran
%Y Abercrombie, Gavin
%Y Basile, Valerio
%Y Leonardelli, Elisa
%Y Frenda, Simona
%S Proceedings of the the fifth edition of NLPerspectives
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F gurushankar-saisudha-bergler-2026-modeling
%X Understanding text through multiple perspectives is essential in domains such as healthcare community question answering, where answers frequently contain heterogeneous viewpoints, including experiences, suggestions, causes, follow-up questions, and informational claims. We present a unified perspective-conditioned framework for both span identification and perspective-aware summarization on the PerAnsSumm dataset. Our approach introduces explicit perspective signals into transformer models using two parameter-efficient mechanisms: prefix-conditioned representations and perspective-aware attention layers. We first employ multi-label perspective classification to identify relevant viewpoints, which serve as conditioning signals for downstream tasks. For span identification, we model perspective-specific extraction as a conditioned binary sequence labeling problem. For summarization, we guide generation using perspective-enriched encoder representations. Experiments demonstrate that explicit perspective conditioning substantially improves span detection performance while achieving competitive summarization quality. Notably, perspective-aware attention achieves strong results using only a small fraction of the trainable parameters required by full fine-tuning. Our findings highlight the importance of structured viewpoint modeling and show that explicit perspective control enables efficient and interpretable multi-perspective text understanding.
%R 10.63317/5oecmktyh8bf
%U https://aclanthology.org/2026.nlperspectives-1.12/
%U https://doi.org/10.63317/5oecmktyh8bf
%P 124-135
Markdown (Informal)
[Modeling Perspectives in NLP: Parameter-Efficient Perspective Conditioning for Span Extraction and Summarization](https://aclanthology.org/2026.nlperspectives-1.12/) (Gurushankar Saisudha & Bergler, NLPerspectives 2026)
ACL