@inproceedings{reimer-etal-2021-modern,
title = "Modern Talking in Key Point Analysis: Key Point Matching using Pretrained Encoders",
author = "Reimer, Jan Heinrich and
Luu, Thi Kim Hanh and
Henze, Max and
Ajjour, Yamen",
booktitle = "Proceedings of the 8th Workshop on Argument Mining",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.argmining-1.18",
doi = "10.18653/v1/2021.argmining-1.18",
pages = "175--183",
abstract = "We contribute to the ArgMining 2021 shared task on Quantitative Summarization and Key Point Analysis with two approaches for argument key point matching. For key point matching the task is to decide if a short key point matches the content of an argument with the same topic and stance towards the topic. We approach this task in two ways: First, we develop a simple rule-based baseline matcher by computing token overlap after removing stop words, stemming, and adding synonyms/antonyms. Second, we fine-tune pretrained BERT and RoBERTalanguage models as aregression classifier for only a single epoch. We manually examine errors of our proposed matcher models and find that long arguments are harder to classify. Our fine-tuned RoBERTa-Base model achieves a mean average precision score of 0.913, the best score for strict labels of all participating teams.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="reimer-etal-2021-modern">
<titleInfo>
<title>Modern Talking in Key Point Analysis: Key Point Matching using Pretrained Encoders</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="given">Heinrich</namePart>
<namePart type="family">Reimer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thi</namePart>
<namePart type="given">Kim</namePart>
<namePart type="given">Hanh</namePart>
<namePart type="family">Luu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Max</namePart>
<namePart type="family">Henze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yamen</namePart>
<namePart type="family">Ajjour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Workshop on Argument Mining</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We contribute to the ArgMining 2021 shared task on Quantitative Summarization and Key Point Analysis with two approaches for argument key point matching. For key point matching the task is to decide if a short key point matches the content of an argument with the same topic and stance towards the topic. We approach this task in two ways: First, we develop a simple rule-based baseline matcher by computing token overlap after removing stop words, stemming, and adding synonyms/antonyms. Second, we fine-tune pretrained BERT and RoBERTalanguage models as aregression classifier for only a single epoch. We manually examine errors of our proposed matcher models and find that long arguments are harder to classify. Our fine-tuned RoBERTa-Base model achieves a mean average precision score of 0.913, the best score for strict labels of all participating teams.</abstract>
<identifier type="citekey">reimer-etal-2021-modern</identifier>
<identifier type="doi">10.18653/v1/2021.argmining-1.18</identifier>
<location>
<url>https://aclanthology.org/2021.argmining-1.18</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>175</start>
<end>183</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Modern Talking in Key Point Analysis: Key Point Matching using Pretrained Encoders
%A Reimer, Jan Heinrich
%A Luu, Thi Kim Hanh
%A Henze, Max
%A Ajjour, Yamen
%S Proceedings of the 8th Workshop on Argument Mining
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F reimer-etal-2021-modern
%X We contribute to the ArgMining 2021 shared task on Quantitative Summarization and Key Point Analysis with two approaches for argument key point matching. For key point matching the task is to decide if a short key point matches the content of an argument with the same topic and stance towards the topic. We approach this task in two ways: First, we develop a simple rule-based baseline matcher by computing token overlap after removing stop words, stemming, and adding synonyms/antonyms. Second, we fine-tune pretrained BERT and RoBERTalanguage models as aregression classifier for only a single epoch. We manually examine errors of our proposed matcher models and find that long arguments are harder to classify. Our fine-tuned RoBERTa-Base model achieves a mean average precision score of 0.913, the best score for strict labels of all participating teams.
%R 10.18653/v1/2021.argmining-1.18
%U https://aclanthology.org/2021.argmining-1.18
%U https://doi.org/10.18653/v1/2021.argmining-1.18
%P 175-183
Markdown (Informal)
[Modern Talking in Key Point Analysis: Key Point Matching using Pretrained Encoders](https://aclanthology.org/2021.argmining-1.18) (Reimer et al., ArgMining 2021)
ACL