Classifying Argument Component using Deep Learning on English Dataset
Abstract
The argument component is a part of argumentation mining where the study focused on the type of argument like claim and premise. nowadays there are already various argumentation components datasets, and each dataset has different argument component classes. Our focus is on the performance of deep learning architectures, especially on using contextual embedding as the initial layer of the architecture. As a validation, we use six datasets that have different argument components. And also, this research provides a comprehensive comparison among all deep learning architectures by combining multiple layers of deep learning such as combining the Bidirectional Encoder Representations from Transformers (BERT) base model or word embedding as an embedding layer with LSTM, GRU, or CNN. Related to the results of the research, will be discussed at the end of the journal. After conducting several experiments, significant results were obtained in this study with the BERT-BiGRU-CRF architecture.Povzetek: Namen te študije je določiti učinkovitost več modelov na šestih različnih delih podatkov, ki uporabljajo več transformatorjev kot kombinirano ali nezdruženo vdelano plast, kot tudi druge modele globokega učenja.References
Mochales, R. & Moens, M. F. (2011). Argumentation Mining. Artificial Intelligence and Law. 19. 1-22. 10.1007/s10506-010-9104-x.
Schulz, C., Eger, S., Daxenberger, J., Kahse, T., & Gurevych, I. (2018). Multi-Task Learning for Argumentation Mining in Low-Resource Settings. NAACL- HLT.
Lawrence, J. & Reed, C. (2019). Argument Mining: A Survey. Computational Linguistics. 45. 765-818. 10.1162/COLI_a_00364.
Suhartono, D., Gema, A. P., Winton, S., David, T., Fanany, M. I., Arymurthy, A. M. (2020). Argument annotation and analysis using deep learning with attention mechanism in Bahasa Indonesia. Journal of Big Data. 7(90). Springer.
Gema, Aryo & Winton, Suhendro & David, Theodorus & Suhartono, Derwin & Shodiq, Muhsin & Gazali, Wikaria. (2017). It Takes Two To Tango: Modification of Siamese Long Short Term Memory Network with Attention Mechanism in Recognizing Argumentative Relations in Persuasive Essay. Procedia Computer Science. 116. 449-459. 10.1016/j.procs.2017.10.036.
Hunter, Anthony. (2007). Elements of Argumentation. 4. 10.1007/978-3-540-75256-1_3.
Lippi, M., & Torroni, P. (2016). Argumentation Mining: State of the Art and Emerging Trends. ACM Trans. Internet Techn., 16, 10:1-10:25.
Sardianos, C., Katakis, I.M., Petasis, G., & Karkaletsis, V. (2015). Argument Extraction from News. ArgMining@HLT-NAACL.
Stab, C., Kirschner, C., Eckle-Kohler, J., & Gurevych, I. (2014). Argumentation Mining in Persuasive Essays and Scientific Articles from the Discourse Structure Perspective. ArgNLP.
Biran, O., & Rambow, O. (2011). Identifying Justifications in Written Dialogs by Classifying Text as Argumentative. Int. J. Semantic Comput., 5, 363-381.
Palau, R., & Moens, M. (2009). Argumentation mining: the detection, classification and structure of arguments in text. ICAIL.
Lippi, M., & Torroni, P. (2015). Argument Mining: A Machine Learning Perspective. TAFA.
Ruiz-Dolz, R., Barberá, S.H., Alemany, J., & García-Fornes, A. (2020). Transformer- Based Models for Automatic Identification of Argument Relations: A Cross- Domain Evaluation. ArXiv, abs/2011.13187.
Culotta, A., McCallum, A., & Betz, J. (2006). Integrating Probabilistic Extraction Models and Data Mining to Discover Relations and Patterns in Text. HLT-NAACL.
Mayer, T., Cabrio, E., & Villata, S. (2020). Transformer-Based Argument Mining for Healthcare Applications. ECAI.
Hidayaturrahman, Dave, E., Suhartono, D., & Arymurthy, A. M. (2021). Enhancing argumentation component classification using contextual language model. Journal of Big Data, 8(1), [103]. https://doi.org/10.1186/s40537-021-00490-2
Gunawan, W., Suhartono, D., Purnomo, F., & Ongko, A. (2018). Named-Entity Recognition for Indonesian Language using Bidirectional LSTM-CNNs. Procedia Computer Science, 135, 425-432.
Yu, Q., Wang, Z., & Jiang, K. (2020). Research on Text Classification Based on BERT-BiGRU Model. Journal of Physics Conference Series, 2021, vol. 1746, no. 1. doi:10.1088/1742-6596/1746/1/012019.
Tobias, M., Elena, C., & Serena, V. (2020) Transformer-based Argument Mining for Healthcare Applications. In Proceedings of the 24th European Conference on Artificial Intelligence (ECAI 2020), Santiago de Compostela, Spain.
Qin, Q., Zhao, S., & Liu, C. (2021). A BERT-BiGRU-CRF Model for Entity Recognition of Chinese Electronic Medical Records. Complexity. 2021. 1-11. 10.1155/2021/6631837.
Toulmin, S. (2008). The Uses of Argument, Updated Edition.
Lytos, A., Lagkas, T., Sarigiannidis, P., & Bontcheva, K. (2019). The evolution of argumentation mining: From models to social media and emerging tools. ArXiv, abs/1907.02258.
Boltuzic, F., & Šnajder, J. (2015). Identifying Prominent Arguments in Online Debates Using Semantic Textual Similarity. ArgMining@HLT-NAACL.
Winata, R., Haryono, E. G., Suhartono, D. (2021). Toward Better Argument Component Classification in English Essays. ICIC Express Letters. vol. 12. 111-119.
Stab, C., & Gurevych, I. (2014). Identifying Argumentative Discourse Structures in Persuasive Essays. EMNLP.
Kusmantini, H.A., Asror, I., & Bijaksana, M.A. (2019). Argumentation mining: classifying argumentation components with Partial Tree Kernel and Support Vector Machine for constituent trees on imbalanced persuasive essay.
Harly, W., Kwee, R. H., Suhartono, D. (2022). Quantitative Argument Summarization Using Text-to-Text Transfer Transformer. ICIC Express Letters Part B: Applications. vol. 13, 749-756. doi:10.24507/icicelb.13.07.749.
Ratinov, L., & Roth, D. (2009). Design Challenges and Misconceptions in Named Entity Recognition. Conference on Computational Natural Language Learning.
Reed, C., Palau, R., Rowe, G., & Moens, M. (2008). Language Resources for Studying Argument. LREC.
Liu, H., Gao, Y., Lv, P., Li, M., Geng, S., Li, M., & Wang, H. (2017). Using Argument-based Features to Predict and Analyse Review Helpfulness. ArXiv, abs/1707.07279.
Habernal, I., & Gurevych, I. (2017). Argumentation Mining in User-Generated Web Discourse. Computational Linguistics, 43, 125-179.
Habernal, I., Wachsmuth, H., Gurevych, I., & Stein, B. (2017). The Argument Reasoning Comprehension Task. ArXiv, abs/1708.01425.
Sanh, V., Debut, L., Chaumond, J., & Wolf, T. (2019). DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. ArXiv, abs/1910.01108.
Zaheer, M., Guruganesh, G., Dubey, K.A., Ainslie, J., Alberti, C., Ontañón, S., Pham, P., Ravula, A., Wang, Q., Yang, L., & Ahmed, A. (2020). Big Bird: Transformers for Longer Sequences. ArXiv, abs/2007.14062.
DOI:
https://doi.org/10.31449/inf.v47i5.4617Downloads
Published
How to Cite
Issue
Section
License
Authors retain copyright in their work. By submitting to and publishing with Informatica, authors grant the publisher (Slovene Society Informatika) the non-exclusive right to publish, reproduce, and distribute the article and to identify itself as the original publisher.
All articles are published under the Creative Commons Attribution license CC BY 3.0. Under this license, others may share and adapt the work for any purpose, provided appropriate credit is given and changes (if any) are indicated.
Authors may deposit and share the submitted version, accepted manuscript, and published version, provided the original publication in Informatica is properly cited.
