User-Centric Argument Mining with ArgueMapper and Arguebuf

Lenz, Mirko; Bergmann, Ralph

doi:10.3233/faia220176

Cited by 4 publications

(3 citation statements)

References 2 publications

(2 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Before describing both phases of our method, it is important to contextualise our proposal within the area of computational argumentation research. We assume that the whole argument analysis of natural language text has already been carried out: the argumentative discourse has been segmented, the argument components have been classified, and argument relations have been identified among the segmented argumentative text spans (see (Lenz et al, 2020)). Thus, a graph structure can be defined from a given natural language argumentative input.…”

Section: Methodsmentioning

confidence: 99%

Automatic Debate Evaluation with Argumentation Semantics and Natural Language Argument Graph Networks

Ruiz-Dolz,

Heras,

Garcia

2023

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

The lack of annotated data on professional argumentation and complete argumentative debates has led to the oversimplification and the inability of approaching more complex natural language processing tasks. Such is the case of the automatic evaluation of complete professional argumentative debates. In this paper, we propose an original hybrid method to automatically predict the winning stance in this kind of debates. For that purpose, we combine concepts from argumentation theory such as argumentation frameworks and semantics, with Transformer-based architectures and neural graph networks. Furthermore, we obtain promising results that lay the basis on an unexplored new instance of the automatic analysis of natural language arguments.

show abstract

Section: Methodsmentioning

confidence: 99%

Automatic Debate Evaluation with Argumentation Semantics and Natural Language Argument Graph Networks

Ruiz-Dolz,

Heras,

Garcia

2023

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

show abstract

“…Stab and Gurevych (2017) introduced a larger version of the PE corpus and implemented an ILP constrained pipelined approach for AM. Mirko et al (2020) improved upon the pipelined approach for AM introduced by Nguyen and Litman (2018), and further implemented a novel graph construction process to create argument graphs. Recently, Bao et al (2021) proposed a neural transition-based model for component classification and relationship detection, which incrementally builds an argumentation graph by generating a sequence of actions, and can handle both tree and non-tree argumentation structures.…”

Section: Related Workmentioning

confidence: 99%

EDU-AP: Elementary Discourse Unit based Argument Parser

Saha,

Das,

Srihari

2022

Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue

View full text Add to dashboard Cite

Neural approaches to end-to-end argument mining (AM) are often formulated as dependency parsing (DP), which relies on token-level sequence labeling and intricate post-processing for extracting argumentative structures from text. Although such methods yield reasonable results, operating solely with tokens increases the possibility of discontinuous and overly segmented structures due to minor inconsistencies in token level predictions. In this paper, we propose EDU-AP, an end-to-end argument parser, that alleviates such problems in dependency-based methods by exploiting the intrinsic relationship between elementary discourse units (EDUs) and argumentative discourse units (ADUs) and operates at both token and EDU level granularity. Further, appropriately using contextual information, along with optimizing a novel objective function during training, EDU-AP achieves significant improvements across all four tasks of AM compared to existing dependency-based methods.

show abstract

“…This approach takes probabilistic information that can be acquired using machine learning models and creates a representative argumentation framework. Finally, work by Lenz et al [211] presents a complete argument mining pipeline to automatically generate argumentation graphs from natural language text.…”

Section: Argument Graph Miningmentioning

confidence: 99%

Computational Argumentation for the Automatic Analysis of Argumentative Discourse and Human Persuasion

Dolz¹

View full text Add to dashboard Cite

Finalment, m'agradaria acabar expressant els meus agraïments a les dues persones fonamentals en la definició i consolidació de la meua carrera acadèmica, les meues tutores. Des que vaig comenc ¸ar a treballar al VRAIN, el suport rebut per part d'Ana i de Stella ha sigut incommensurable. Sota la seua tutela excepcional ha sigut possible desenvolupar totes les idees i propostes presents en aquesta tesi doctoral.Moltes gràcies a totes i tots.Ramon

show abstract

User-Centric Argument Mining with ArgueMapper and Arguebuf

Cited by 4 publications

References 2 publications

Automatic Debate Evaluation with Argumentation Semantics and Natural Language Argument Graph Networks

Automatic Debate Evaluation with Argumentation Semantics and Natural Language Argument Graph Networks

EDU-AP: Elementary Discourse Unit based Argument Parser

Computational Argumentation for the Automatic Analysis of Argumentative Discourse and Human Persuasion

Contact Info

Product

Resources

About