Argument Component Classification by Relation Identification by Neural Network and TextRank

Deguchi, Mamoru; Yamaguchi, Kazunori

doi:10.18653/v1/w19-4510

Cited by 4 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From our survey, only addressed the argument relation recognition task. This is not the case in recent word embedding-based deep learning methods, which deal with the three tasks as sequence tagging problems, by commonly following the BIO tagging format, e.g., (Deguchi and Yamaguchi, 2019;Mayer et al, 2020).…”

Section: Related Workmentioning

confidence: 99%

Proceedings of the 10th Workshop on Argument Mining

2023

View full text Add to dashboard Cite

Previous work on the automatic identification of fallacies in natural language text has typically approached the problem in constrained experimental setups that make it difficult to understand the applicability and usefulness of the proposals in the real world. In this paper, we present the first analysis of the limitations that these data-driven approaches could show in real situations. For that purpose, we first create a validation corpus consisting of natural language argumentation schemes. Second, we provide new empirical results to the emerging task of identifying fallacies in natural language text. Third, we analyse the errors observed outside of the testing data domains considering the new validation corpus. Finally, we point out some important limitations observed in our analysis that should be taken into account in future research in this topic. Specifically, if we want to deploy these systems in the Wild. Arg. Scheme CQs Natural Language Argumentation Schemes AFEO ✓ Major Premise: "Prof Whittaker is a professor of virology at the Cornell University College" Minor Premise: "Prof Whittaker said that viruses can be spread by sneezing" Conclusion: "Viruses can be spread by sneezing" AFEO ✗ Major Premise: "Stephen Hawking was an expert on AI" Minor Premise: "Stephen Hawking said that AI could spell the end of the human race" Conclusion: "AI could spell the end of the human race" AFPK ✓ Major Premise: "Alice lives in New York" Minor Premise: "Alice says that New York City Hall is in Lower Manhattan" Conclusion: "New York City Hall is in Lower Manhattan" AFPK ✗ Major Premise: "David is a cab driver in London" Minor Premise: "David says that the best way to get to Tower Bridge is by cab" Conclusion: "The best way to get to Tower Bridge is by cab" AFPP ✓ Major Premise: "Most people wear black clothes at a funeral" Minor Premise: "If most people wear black clothes at a funeral, that is acceptable to do" Conclusion: "It is acceptable to wear black clothes at a funeral" AFPP ✗ Major Premise: "Most people drive at least 10 miles per hour over the speed limit" Minor Premise: "If most people drive at least 10 miles per hour over the speed... ...limit, that is acceptable to do" Conclusion: "It is acceptable to drive at least 10 miles per hour over the speed limit" AFPO ✓ General Acceptance Premise: "The majority of climate scientists agree that humans... ...are causing global warming and climate change" Presumption Premise: "If the majority of climate scientists agree that humans... ...are causing global warming and climate change, there is a reason to believe that is true" Conclusion: "There is reason to believe that humans... ...are causing global warming and climate change" AFPO ✗General Acceptance Premise: "The majority of people we asked agreed that the Earth may be flat " Presumption Premise: "If the majority of people we asked agreed that the Earth... ...may be flat, there is a reason to believe that is true" Conclusion: "There is reason to believe that the Earth may be flat" SSAS ✓ FirstStep Premise: "I should ...

show abstract

Section: Related Workmentioning

confidence: 99%

Proceedings of the 10th Workshop on Argument Mining

2023

View full text Add to dashboard Cite

show abstract

“…From our survey, only Du et al (2017) addressed the argument relation recognition task. This is not the case in recent word embedding-based deep learning methods, which deal with the three tasks as sequence tagging problems, by commonly following the BIO tagging format, e.g., (Deguchi and Yamaguchi, 2019;Mayer et al, 2020).…”

Section: Related Workmentioning

confidence: 99%

Dimensionality Reduction for Machine Learning-based Argument Mining

Segura-Tinoco,

Cantador

2023

Proceedings of the 10th Workshop on Argument Mining

View full text Add to dashboard Cite

Recent approaches to argument mining have focused on training machine learning algorithms from annotated text corpora, utilizing as input high-dimensional linguistic feature vectors. Differently to previous work, in this paper, we preliminarily investigate the potential benefits of reducing the dimensionality of the input data. Through an empirical study, testing SVD, PCA and LDA techniques on a new argumentative corpus in Spanish for an underexplored domain (e-participation), and using a novel, rich argument model, we show positive results in terms of both computation efficiency and argumentative information extraction effectiveness, for the three major argument mining tasks: argumentative fragment detection, argument component classification, and argumentative relation recognition. On a space with dimension around 3-4% of the number of input features, the argument mining methods are able to reach 95-97% of the performance achieved by using the entire corpus, and even surpass it in some cases.

show abstract

“…Inspired by PageRank (Page et al, 1999), the TextRank algorithm (Mihalcea and Tarau, 2004) is a content extraction algorithm that represents texts as graphs for sentence and keyword extraction purposes and uses the PageRank algorithm to rank sentences or keywords. Since TextRank was first released, it has been applied to tasks such as summarization (Mallick et al, 2019;Barrios et al, 2015;Son and Shin, 2018), keyword extraction (Wen et al, 2016;Jianfei and Jiangzhen, 2016), opinion mining (Petasis and Karkaletsis, 2016;Deguchi and Yamaguchi, 2019), credibility assessment (Balcerzak et al, 2014) and others.…”

Section: Textrankmentioning

confidence: 99%

“…TextRank (Mihalcea and Tarau, 2004) is a light-weight unsupervised graph-based content extraction algorithm that was initially designed for summarization and keyword extraction applications. Since its introduction, it has been adapted and used in numerous other applications and settings, including opinion mining (Petasis and Karkaletsis, 2016;Deguchi and Yamaguchi, 2019), credibility assessment (Balcerzak et al, 2014) and lyrics summarization (Son and Shin, 2018), among others. Most recently, TextRank has been included in the latest release of the popular spaCy library.…”

Section: Introductionmentioning

confidence: 99%

Biased TextRank: Unsupervised Graph-Based Content Extraction

Kazemi¹,

Pérez-Rosas²,

Mihalcea³

2020

Proceedings of the 28th International Conference on Computational Linguistics

View full text Add to dashboard Cite

We introduce Biased TextRank, a graph-based content extraction method inspired by the popular TextRank algorithm that ranks text spans according to their importance for language processing tasks and according to their relevance to an input "focus." Biased TextRank enables focused content extraction for text by modifying the random restarts in the execution of TextRank. The random restart probabilities are assigned based on the relevance of the graph nodes to the focus of the task. We present two applications of Biased TextRank: focused summarization and explanation extraction, and show that our algorithm leads to improved performance on two different datasets by significant ROUGE-N score margins. Much like its predecessor, Biased TextRank is unsupervised, easy to implement and orders of magnitude faster and lighter than current state-ofthe-art Natural Language Processing methods for similar tasks.

show abstract

Argument Component Classification by Relation Identification by Neural Network and TextRank

Cited by 4 publications

References 12 publications

Proceedings of the 10th Workshop on Argument Mining

Proceedings of the 10th Workshop on Argument Mining

Dimensionality Reduction for Machine Learning-based Argument Mining

Biased TextRank: Unsupervised Graph-Based Content Extraction

Contact Info

Product

Resources

About