@inproceedings{kruff-tran-2023-billie,
title = "Billie-Newman at {S}em{E}val-2023 Task 5: Clickbait Classification and Question Answering with Pre-Trained Language Models, Named Entity Recognition and Rule-Based Approaches",
author = "Kruff, Andreas and
Tran, Anh Huy",
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-1.213",
doi = "10.18653/v1/2023.semeval-1.213",
pages = "1542--1550",
abstract = "In this paper, we describe the implementations of our systems for the SemEval-2023 Task 5 {`}Clickbait Spoiling{'}, which involves the classification of clickbait posts in sub-task 1 and the spoiler generation and question answering of clickbait posts in sub-task 2, ultimately achieving a balanced accuracy of 0.593 and a BLEU score of 0.322 on the test datasets in sub-task 1 and sub-task 2 respectively. For this, we propose the usage of RoBERTa transformer models and modify them for each specific downstream task. In sub-task 1, we use the pre-trained RoBERTa model and use it in conjunction with NER, a spoiler-title ratio, a regex check for enumerations and lists and the use of input reformulation. In sub-task 2, we propose the usage of the RoBERTa-SQuAD2.0 model for extractive question answering in combination with a contextual rule-based approach for multi-type spoilers in order to generate spoiler answers.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kruff-tran-2023-billie">
<titleInfo>
<title>Billie-Newman at SemEval-2023 Task 5: Clickbait Classification and Question Answering with Pre-Trained Language Models, Named Entity Recognition and Rule-Based Approaches</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Kruff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anh</namePart>
<namePart type="given">Huy</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>In this paper, we describe the implementations of our systems for the SemEval-2023 Task 5 ‘Clickbait Spoiling’, which involves the classification of clickbait posts in sub-task 1 and the spoiler generation and question answering of clickbait posts in sub-task 2, ultimately achieving a balanced accuracy of 0.593 and a BLEU score of 0.322 on the test datasets in sub-task 1 and sub-task 2 respectively. For this, we propose the usage of RoBERTa transformer models and modify them for each specific downstream task. In sub-task 1, we use the pre-trained RoBERTa model and use it in conjunction with NER, a spoiler-title ratio, a regex check for enumerations and lists and the use of input reformulation. In sub-task 2, we propose the usage of the RoBERTa-SQuAD2.0 model for extractive question answering in combination with a contextual rule-based approach for multi-type spoilers in order to generate spoiler answers.</abstract>
<identifier type="citekey">kruff-tran-2023-billie</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.213</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.213</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1542</start>
<end>1550</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Billie-Newman at SemEval-2023 Task 5: Clickbait Classification and Question Answering with Pre-Trained Language Models, Named Entity Recognition and Rule-Based Approaches
%A Kruff, Andreas
%A Tran, Anh Huy
%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 kruff-tran-2023-billie
%X In this paper, we describe the implementations of our systems for the SemEval-2023 Task 5 ‘Clickbait Spoiling’, which involves the classification of clickbait posts in sub-task 1 and the spoiler generation and question answering of clickbait posts in sub-task 2, ultimately achieving a balanced accuracy of 0.593 and a BLEU score of 0.322 on the test datasets in sub-task 1 and sub-task 2 respectively. For this, we propose the usage of RoBERTa transformer models and modify them for each specific downstream task. In sub-task 1, we use the pre-trained RoBERTa model and use it in conjunction with NER, a spoiler-title ratio, a regex check for enumerations and lists and the use of input reformulation. In sub-task 2, we propose the usage of the RoBERTa-SQuAD2.0 model for extractive question answering in combination with a contextual rule-based approach for multi-type spoilers in order to generate spoiler answers.
%R 10.18653/v1/2023.semeval-1.213
%U https://aclanthology.org/2023.semeval-1.213
%U https://doi.org/10.18653/v1/2023.semeval-1.213
%P 1542-1550
Markdown (Informal)
[Billie-Newman at SemEval-2023 Task 5: Clickbait Classification and Question Answering with Pre-Trained Language Models, Named Entity Recognition and Rule-Based Approaches](https://aclanthology.org/2023.semeval-1.213) (Kruff & Tran, SemEval 2023)
ACL