@inproceedings{amal-etal-2026-ai,
title = "{AI}@{UMS} at {S}em{E}val-2026 Task 6: Handling Long Question-Answer Pairs with Sliding Window Models for Clarity and Evasion Analysis",
author = "Amal, Ikhlasul and
Zafar, Zia Ul and
Firdaus, Choiru and
Pamungkas, Endang",
editor = "Kochmar, Ekaterina and
Ghosh, Debanjan and
North, Kai and
Komachi, Mamoru",
booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.semeval-1.437/",
pages = "3544--3548",
ISBN = "979-8-89176-414-9",
abstract = "This paper presents the AI@UMS system for SemEval-2026 Task 6: CLARITY - Unmasking Political Question Evasions. The task requires classifying question-answer (QA) pairs from political interviews along two dimensions: clarity level (Subtask 1) and evasion technique (Subtask 2). A key challenge is that political interview transcripts often exceed the 512-token input limit of standard transformer encoder models. We address this with a sliding-window fine-tuning strategy applied to roberta-base, where each QA pair is segmented into overlapping windows of 512 tokens with a stride of 256 tokens. Per-window predictions are aggregated via softmax probability averaging across multiple windows and across an ensemble of three independently trained models with different random seeds. We further employ class-weighted focal-inspired loss and label smoothing to mitigate the pronounced class imbalance in both subtasks. Our system achieves macro F1 scores of 0.62 (Subtask 1) and 0.48 (Subtask 2) on the official evaluation set."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="amal-etal-2026-ai">
<titleInfo>
<title>AI@UMS at SemEval-2026 Task 6: Handling Long Question-Answer Pairs with Sliding Window Models for Clarity and Evasion Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ikhlasul</namePart>
<namePart type="family">Amal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zia</namePart>
<namePart type="given">Ul</namePart>
<namePart type="family">Zafar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Choiru</namePart>
<namePart type="family">Firdaus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Endang</namePart>
<namePart type="family">Pamungkas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Workshop on Semantic Evaluation (2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-414-9</identifier>
</relatedItem>
<abstract>This paper presents the AI@UMS system for SemEval-2026 Task 6: CLARITY - Unmasking Political Question Evasions. The task requires classifying question-answer (QA) pairs from political interviews along two dimensions: clarity level (Subtask 1) and evasion technique (Subtask 2). A key challenge is that political interview transcripts often exceed the 512-token input limit of standard transformer encoder models. We address this with a sliding-window fine-tuning strategy applied to roberta-base, where each QA pair is segmented into overlapping windows of 512 tokens with a stride of 256 tokens. Per-window predictions are aggregated via softmax probability averaging across multiple windows and across an ensemble of three independently trained models with different random seeds. We further employ class-weighted focal-inspired loss and label smoothing to mitigate the pronounced class imbalance in both subtasks. Our system achieves macro F1 scores of 0.62 (Subtask 1) and 0.48 (Subtask 2) on the official evaluation set.</abstract>
<identifier type="citekey">amal-etal-2026-ai</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.437/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>3544</start>
<end>3548</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AI@UMS at SemEval-2026 Task 6: Handling Long Question-Answer Pairs with Sliding Window Models for Clarity and Evasion Analysis
%A Amal, Ikhlasul
%A Zafar, Zia Ul
%A Firdaus, Choiru
%A Pamungkas, Endang
%Y Kochmar, Ekaterina
%Y Ghosh, Debanjan
%Y North, Kai
%Y Komachi, Mamoru
%S Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-414-9
%F amal-etal-2026-ai
%X This paper presents the AI@UMS system for SemEval-2026 Task 6: CLARITY - Unmasking Political Question Evasions. The task requires classifying question-answer (QA) pairs from political interviews along two dimensions: clarity level (Subtask 1) and evasion technique (Subtask 2). A key challenge is that political interview transcripts often exceed the 512-token input limit of standard transformer encoder models. We address this with a sliding-window fine-tuning strategy applied to roberta-base, where each QA pair is segmented into overlapping windows of 512 tokens with a stride of 256 tokens. Per-window predictions are aggregated via softmax probability averaging across multiple windows and across an ensemble of three independently trained models with different random seeds. We further employ class-weighted focal-inspired loss and label smoothing to mitigate the pronounced class imbalance in both subtasks. Our system achieves macro F1 scores of 0.62 (Subtask 1) and 0.48 (Subtask 2) on the official evaluation set.
%U https://aclanthology.org/2026.semeval-1.437/
%P 3544-3548
Markdown (Informal)
[AI@UMS at SemEval-2026 Task 6: Handling Long Question-Answer Pairs with Sliding Window Models for Clarity and Evasion Analysis](https://aclanthology.org/2026.semeval-1.437/) (Amal et al., SemEval 2026)
ACL