Argument Extraction for Key Point Generation Using MMR-Based Methods
When people debate, they want to familiarize themselves with a whole range of arguments about a given topic in order to deepen their knowledge and inspire new claims. However, the amount of differently phrased arguments is humongous, making the process of processing them time-consuming. In spite of...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2021-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9490211/ |
id |
doaj-3a24efbff369436cb8485364adadca1c |
---|---|
record_format |
Article |
spelling |
doaj-3a24efbff369436cb8485364adadca1c2021-07-27T23:00:31ZengIEEEIEEE Access2169-35362021-01-01910309110310910.1109/ACCESS.2021.30979769490211Argument Extraction for Key Point Generation Using MMR-Based MethodsDaiki Shirafuji0Rafal Rzepka1https://orcid.org/0000-0002-8274-0875Kenji Araki2https://orcid.org/0000-0001-9668-1610Graduate School of Information Science and Technology, Hokkaido University, Hokkaido, JapanFaculty of Information Science and Technology, Hokkaido University, Hokkaido, JapanFaculty of Information Science and Technology, Hokkaido University, Hokkaido, JapanWhen people debate, they want to familiarize themselves with a whole range of arguments about a given topic in order to deepen their knowledge and inspire new claims. However, the amount of differently phrased arguments is humongous, making the process of processing them time-consuming. In spite of many works on using arguments (e.g. counter-argument generation), there is only a few studies on argument aggregation. To address this problem, we propose a new task in argument mining – Argument Extraction, which gathers similar arguments into <italic>key points</italic>, usually single sentences describing a set of arguments for a given debate topic. Such a short summary of related arguments has been manually created in previous research, while in our research key point generation becomes fully automatic, saving time and cost. As the first step of key point generation we explore existing similarity calculation methods, i.e. Sentence-BERT and MoverScore to investigate their performance. Next, we propose a combination of argument similarity and Maximal Marginal Relevance (MMR) for extracting key phrases to be utilized in our novel task of Argument Extraction. Experimental results show that MoverScore-based MMR outperforms strong baselines covering 72.5% of arguments when eleven or more arguments are extracted. This percentage is almost identical with the cover rate of human-made key points.https://ieeexplore.ieee.org/document/9490211/Argument aggregationargument miningkey pointsmachine learningnatural language processingtext summarization |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Daiki Shirafuji Rafal Rzepka Kenji Araki |
spellingShingle |
Daiki Shirafuji Rafal Rzepka Kenji Araki Argument Extraction for Key Point Generation Using MMR-Based Methods IEEE Access Argument aggregation argument mining key points machine learning natural language processing text summarization |
author_facet |
Daiki Shirafuji Rafal Rzepka Kenji Araki |
author_sort |
Daiki Shirafuji |
title |
Argument Extraction for Key Point Generation Using MMR-Based Methods |
title_short |
Argument Extraction for Key Point Generation Using MMR-Based Methods |
title_full |
Argument Extraction for Key Point Generation Using MMR-Based Methods |
title_fullStr |
Argument Extraction for Key Point Generation Using MMR-Based Methods |
title_full_unstemmed |
Argument Extraction for Key Point Generation Using MMR-Based Methods |
title_sort |
argument extraction for key point generation using mmr-based methods |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2021-01-01 |
description |
When people debate, they want to familiarize themselves with a whole range of arguments about a given topic in order to deepen their knowledge and inspire new claims. However, the amount of differently phrased arguments is humongous, making the process of processing them time-consuming. In spite of many works on using arguments (e.g. counter-argument generation), there is only a few studies on argument aggregation. To address this problem, we propose a new task in argument mining – Argument Extraction, which gathers similar arguments into <italic>key points</italic>, usually single sentences describing a set of arguments for a given debate topic. Such a short summary of related arguments has been manually created in previous research, while in our research key point generation becomes fully automatic, saving time and cost. As the first step of key point generation we explore existing similarity calculation methods, i.e. Sentence-BERT and MoverScore to investigate their performance. Next, we propose a combination of argument similarity and Maximal Marginal Relevance (MMR) for extracting key phrases to be utilized in our novel task of Argument Extraction. Experimental results show that MoverScore-based MMR outperforms strong baselines covering 72.5% of arguments when eleven or more arguments are extracted. This percentage is almost identical with the cover rate of human-made key points. |
topic |
Argument aggregation argument mining key points machine learning natural language processing text summarization |
url |
https://ieeexplore.ieee.org/document/9490211/ |
work_keys_str_mv |
AT daikishirafuji argumentextractionforkeypointgenerationusingmmrbasedmethods AT rafalrzepka argumentextractionforkeypointgenerationusingmmrbasedmethods AT kenjiaraki argumentextractionforkeypointgenerationusingmmrbasedmethods |
_version_ |
1721279256180293632 |