@inproceedings{spreitzer-tran-2023-stephen,
title = "Stephen Colbert at {S}em{E}val-2023 Task 5: Using Markup for Classifying Clickbait",
author = "Spreitzer, Sabrina and
Tran, Hoai Nam",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Da San Martino, Giovanni and
Tayyar Madabushi, Harish and
Kumar, Ritesh and
Sartori, Elisa},
booktitle = "Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.semeval-1.254",
doi = "10.18653/v1/2023.semeval-1.254",
pages = "1844--1848",
abstract = "For SemEval-2023 Task 5, we have submitted three DeBERTaV3[LARGE] models to tackle the first subtask, classifying spoiler types (passage, phrase, multi) of clickbait web articles. The choice of basic parameters like sequence length with BERT[BASE] uncased and further approaches were then tested with DeBERTaV3[BASE] only moving the most promising ones to DeBERTaV3[LARGE]. Our research showed that information-placement on webpages is often optimized regarding e.g. ad-placement Those informations are usually described within the webpages markup which is why we conducted an approach that takes this into account. Overall we could not manage to beat the baseline, which we lead down to three reasons: First we only crawled markup for Huffington Post articles, extracting only p- and a-tags which will not cover enough aspects of a webpages design. Second Huffington Post articles are overrepresented in the given dataset, which, third, shows an imbalance towards the spoiler tags. We highly suggest re-annotating the given dataset to use markup-optimized models like MarkupLM or TIE and to clear it from embedded articles like {``}Yahoo{''} or archives like {``}archive.is{''} or {``}web.archive{''} to avoid noise. Also, the imbalance should be tackled by adding articles from sources other than Huffington Post, considering that also multi-tagged entries should be balanced towards passage- and phrase-tagged ones.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="spreitzer-tran-2023-stephen">
<titleInfo>
<title>Stephen Colbert at SemEval-2023 Task 5: Using Markup for Classifying Clickbait</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sabrina</namePart>
<namePart type="family">Spreitzer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hoai</namePart>
<namePart type="given">Nam</namePart>
<namePart type="family">Tran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="family">Sartori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>For SemEval-2023 Task 5, we have submitted three DeBERTaV3[LARGE] models to tackle the first subtask, classifying spoiler types (passage, phrase, multi) of clickbait web articles. The choice of basic parameters like sequence length with BERT[BASE] uncased and further approaches were then tested with DeBERTaV3[BASE] only moving the most promising ones to DeBERTaV3[LARGE]. Our research showed that information-placement on webpages is often optimized regarding e.g. ad-placement Those informations are usually described within the webpages markup which is why we conducted an approach that takes this into account. Overall we could not manage to beat the baseline, which we lead down to three reasons: First we only crawled markup for Huffington Post articles, extracting only p- and a-tags which will not cover enough aspects of a webpages design. Second Huffington Post articles are overrepresented in the given dataset, which, third, shows an imbalance towards the spoiler tags. We highly suggest re-annotating the given dataset to use markup-optimized models like MarkupLM or TIE and to clear it from embedded articles like “Yahoo” or archives like “archive.is” or “web.archive” to avoid noise. Also, the imbalance should be tackled by adding articles from sources other than Huffington Post, considering that also multi-tagged entries should be balanced towards passage- and phrase-tagged ones.</abstract>
<identifier type="citekey">spreitzer-tran-2023-stephen</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.254</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.254</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1844</start>
<end>1848</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Stephen Colbert at SemEval-2023 Task 5: Using Markup for Classifying Clickbait
%A Spreitzer, Sabrina
%A Tran, Hoai Nam
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Da San Martino, Giovanni
%Y Tayyar Madabushi, Harish
%Y Kumar, Ritesh
%Y Sartori, Elisa
%S Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F spreitzer-tran-2023-stephen
%X For SemEval-2023 Task 5, we have submitted three DeBERTaV3[LARGE] models to tackle the first subtask, classifying spoiler types (passage, phrase, multi) of clickbait web articles. The choice of basic parameters like sequence length with BERT[BASE] uncased and further approaches were then tested with DeBERTaV3[BASE] only moving the most promising ones to DeBERTaV3[LARGE]. Our research showed that information-placement on webpages is often optimized regarding e.g. ad-placement Those informations are usually described within the webpages markup which is why we conducted an approach that takes this into account. Overall we could not manage to beat the baseline, which we lead down to three reasons: First we only crawled markup for Huffington Post articles, extracting only p- and a-tags which will not cover enough aspects of a webpages design. Second Huffington Post articles are overrepresented in the given dataset, which, third, shows an imbalance towards the spoiler tags. We highly suggest re-annotating the given dataset to use markup-optimized models like MarkupLM or TIE and to clear it from embedded articles like “Yahoo” or archives like “archive.is” or “web.archive” to avoid noise. Also, the imbalance should be tackled by adding articles from sources other than Huffington Post, considering that also multi-tagged entries should be balanced towards passage- and phrase-tagged ones.
%R 10.18653/v1/2023.semeval-1.254
%U https://aclanthology.org/2023.semeval-1.254
%U https://doi.org/10.18653/v1/2023.semeval-1.254
%P 1844-1848
Markdown (Informal)
[Stephen Colbert at SemEval-2023 Task 5: Using Markup for Classifying Clickbait](https://aclanthology.org/2023.semeval-1.254) (Spreitzer & Tran, SemEval 2023)
ACL