Skip to main content
main-content

Tipp

Weitere Kapitel dieses Buchs durch Wischen aufrufen

2021 | OriginalPaper | Buchkapitel

A Stacking Approach for Cross-Domain Argument Identification

verfasst von: Alaa Alhamzeh, Mohamed Bouhaouel, Előd Egyed-Zsigmond, Jelena Mitrović, Lionel Brunie, Harald Kosch

Erschienen in: Database and Expert Systems Applications

Verlag: Springer International Publishing

share
TEILEN

Abstract

Argument identification is the cornerstone of a complete argument mining pipeline. Furthermore, it is the essential key for a wide spectrum of applications such as decision making, assisted writing, and legal counselling. Nevertheless, most existing argument mining approaches are limited to a single, specific domain. The problem of building a robust system whose models are able to generalize over heterogeneous datasets remains fairly unexplored. In this paper, we tackle the argument identification task on two different datasets (Student Essays and Web Discourse), following two approaches: a classical machine learning approach and a DistilBert-based approach. Moreover, this paper sheds light on a new direction for researchers in this domain since we validate the principle of ensemble learning. In other words, we show that combining multiple approaches via a well stacked model improves the system performance. The results are very promising with respect to the recent findings in the literature.
Fußnoten
2
We used Transformers from huggingface.co for our experiments.
 
3
Here is an example (from Essays dataset) of an argument sentence that SVM fails to identify while DistilBERT succeeds: “Personally, I think both government and common people should have the responsibility for the environment, but we need to analyze some specific situations.”
 
Literatur
1.
Zurück zum Zitat Govier, T.: A Practical Study of Argument. Wadsworth, Belmont (2001) Govier, T.: A Practical Study of Argument. Wadsworth, Belmont (2001)
2.
Zurück zum Zitat Missimer, C.A.: Good Arguments: An Introduction to Critical Thinking. Prentice Hall, Englewood Cliffs (1995) Missimer, C.A.: Good Arguments: An Introduction to Critical Thinking. Prentice Hall, Englewood Cliffs (1995)
3.
Zurück zum Zitat Stab, C., Gurevych, I.: Identifying argumentative discourse structures in persuasive essays. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 46–56 (2014) Stab, C., Gurevych, I.: Identifying argumentative discourse structures in persuasive essays. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 46–56 (2014)
4.
Zurück zum Zitat Wambsganss, T., Molyndris, N., Söllner, M.: Unlocking transfer learning in argumentation mining: a domain-independent modelling approach. In: 15th International Conference on Wirtschaftsinformatik (2020) Wambsganss, T., Molyndris, N., Söllner, M.: Unlocking transfer learning in argumentation mining: a domain-independent modelling approach. In: 15th International Conference on Wirtschaftsinformatik (2020)
5.
Zurück zum Zitat Reimers, N., Schiller, B., Beck, T., Daxenberger, J., Stab, C., Gurevych, I.: Classification and clustering of arguments with contextualized word embeddings. arXiv preprint arXiv:​1906.​09821 (2019) Reimers, N., Schiller, B., Beck, T., Daxenberger, J., Stab, C., Gurevych, I.: Classification and clustering of arguments with contextualized word embeddings. arXiv preprint arXiv:​1906.​09821 (2019)
7.
Zurück zum Zitat Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995) MATH Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995) MATH
8.
Zurück zum Zitat Sanh, V., Debut, L., Chaumond, J., Wolf, T.: Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter. arXiv preprint arXiv:​1910.​01108 (2019) Sanh, V., Debut, L., Chaumond, J., Wolf, T.: Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter. arXiv preprint arXiv:​1910.​01108 (2019)
9.
Zurück zum Zitat Sagi, O., Rokach, L.: Ensemble learning: a survey. Wiley Interdisc. Rev. Data Mining Knowl. Disc. 8(4), e1249 (2018) Sagi, O., Rokach, L.: Ensemble learning: a survey. Wiley Interdisc. Rev. Data Mining Knowl. Disc. 8(4), e1249 (2018)
10.
Zurück zum Zitat Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:​1810.​04805 (2018) Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:​1810.​04805 (2018)
11.
Zurück zum Zitat Wolf, T., et al.: Transformers: state-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38–45 (2020) Wolf, T., et al.: Transformers: state-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38–45 (2020)
12.
Zurück zum Zitat Moens, M.-F., Boiy, E., Palau, R.M., Reed, C.: Automatic detection of arguments in legal texts. In: Proceedings of the 11th International Conference on Artificial Intelligence and Law, pp. 225–230 (2007) Moens, M.-F., Boiy, E., Palau, R.M., Reed, C.: Automatic detection of arguments in legal texts. In: Proceedings of the 11th International Conference on Artificial Intelligence and Law, pp. 225–230 (2007)
13.
Zurück zum Zitat Palau, R.M., Moens, M.-F.: Argumentation mining: the detection, classification and structure of arguments in text. In: Proceedings of the 12th International Conference on Artificial Intelligence and Law, pp. 98–107 (2009) Palau, R.M., Moens, M.-F.: Argumentation mining: the detection, classification and structure of arguments in text. In: Proceedings of the 12th International Conference on Artificial Intelligence and Law, pp. 98–107 (2009)
14.
Zurück zum Zitat Stab, C., Gurevych, I.: Annotating argument components and relations in persuasive essays. In: Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers, pp. 1501–1510 (2014) Stab, C., Gurevych, I.: Annotating argument components and relations in persuasive essays. In: Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers, pp. 1501–1510 (2014)
15.
Zurück zum Zitat Stab, C., Gurevych, I.: Parsing argumentation structures in persuasive essays. Comput. Linguist. 43(3), 619–659 (2017) MathSciNetCrossRef Stab, C., Gurevych, I.: Parsing argumentation structures in persuasive essays. Comput. Linguist. 43(3), 619–659 (2017) MathSciNetCrossRef
16.
Zurück zum Zitat Habernal, I., Gurevych, I.: Argumentation mining in user-generated web discourse. Comput. Linguist. 43(1), 125–179 (2017) MathSciNetCrossRef Habernal, I., Gurevych, I.: Argumentation mining in user-generated web discourse. Comput. Linguist. 43(1), 125–179 (2017) MathSciNetCrossRef
17.
Zurück zum Zitat Daxenberger, J., Eger, S., Habernal, I., Stab, C., Gurevych, I.: What is the essence of a claim? Cross-domain claim identification. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 2055–2066, Copenhagen, Denmark, September 2017. Association for Computational Linguistics Daxenberger, J., Eger, S., Habernal, I., Stab, C., Gurevych, I.: What is the essence of a claim? Cross-domain claim identification. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 2055–2066, Copenhagen, Denmark, September 2017. Association for Computational Linguistics
18.
Zurück zum Zitat Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2009) CrossRef Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2009) CrossRef
19.
Zurück zum Zitat Liga, D., Palmirani, M.: Transfer learning with sentence embeddings for argumentative evidence classification (2020) Liga, D., Palmirani, M.: Transfer learning with sentence embeddings for argumentative evidence classification (2020)
20.
Zurück zum Zitat Van der Laan, M.J., Polley, E.C., Hubbard, A.E.: Super learner (2007) Van der Laan, M.J., Polley, E.C., Hubbard, A.E.: Super learner (2007)
21.
Zurück zum Zitat Goubin, R., Lefeuvre, D., Alhamzeh, A., Mitrovic, J., Egyed-Zsigmond, E., Fossi, L.G.: Bots and gender profiling using a multi-layer architecture. In: CLEF (Working Notes) (2019) Goubin, R., Lefeuvre, D., Alhamzeh, A., Mitrovic, J., Egyed-Zsigmond, E., Fossi, L.G.: Bots and gender profiling using a multi-layer architecture. In: CLEF (Working Notes) (2019)
22.
Zurück zum Zitat Ciccone, G., Sultan, A., Laporte, L., Egyed-Zsigmond, E., Alhamzeh, A., Granitzer, M.: Stacked gender prediction from tweet texts and images notebook for pan at CLEF 2018. In: CLEF 2018-Conference and Labs of the Evaluation, p. 11p (2018) Ciccone, G., Sultan, A., Laporte, L., Egyed-Zsigmond, E., Alhamzeh, A., Granitzer, M.: Stacked gender prediction from tweet texts and images notebook for pan at CLEF 2018. In: CLEF 2018-Conference and Labs of the Evaluation, p. 11p (2018)
23.
Zurück zum Zitat Toulmin, S.E.: The Uses of Argument. Cambridge University Press, Cambridge (2003) Toulmin, S.E.: The Uses of Argument. Cambridge University Press, Cambridge (2003)
24.
Zurück zum Zitat Knott, A., Dale, R.: Using linguistic phenomena to motivate a set of rhetorical relations, August 1997 Knott, A., Dale, R.: Using linguistic phenomena to motivate a set of rhetorical relations, August 1997
25.
Zurück zum Zitat Caselli, T., Basile, V., Mitrović, J., Kartoziya, I., Granitzer, M.: I feel offended, don’t be abusive! Implicit/explicit messages in offensive and abusive language. In: Proceedings of LREC (2020) Caselli, T., Basile, V., Mitrović, J., Kartoziya, I., Granitzer, M.: I feel offended, don’t be abusive! Implicit/explicit messages in offensive and abusive language. In: Proceedings of LREC (2020)
Metadaten
Titel
A Stacking Approach for Cross-Domain Argument Identification
verfasst von
Alaa Alhamzeh
Mohamed Bouhaouel
Előd Egyed-Zsigmond
Jelena Mitrović
Lionel Brunie
Harald Kosch
Copyright-Jahr
2021
DOI
https://doi.org/10.1007/978-3-030-86472-9_33

Premium Partner