Parsing Argumentation Structures in Persuasive Essays

By Christian Stab, Iryna Gurevych. International Conference on Computational Logic, 2016

521 citations recorded by the source corpus.

In this article, we present a novel approach for parsing argumentation structures. We identify argument components using sequence labeling at the token level and apply a new joint model for detecting argumentation structures. The proposed model globally optimizes argument component types and argumentative relations using Integer Linear Programming. We show that our model significantly outperforms challenging heuristic baselines on two different types of discourse. Moreover, we introduce a novel corpus of persuasive essays annotated with argumentation structures. We show that our annotation scheme and annotation guidelines successfully guide human annotators to substantial agreement.

Subfields: Artificial Intelligence, Information Systems

View Paper: https://www.semanticscholar.org/paper/a74a95a31aa730ce31d9debdd3c82701df98c1fb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

Citations in the corpus

TIARA: A Tool for Annotating Discourse Relations and Sentence Reordering (2020, methodology): “…there are publicly available argumentative essay corpora in which some aspect of discourse structure has been annotated (Peldszus and Stede, 2016; Stab and Gurevych, 2017), sentence reordering annotation is the problem: no ready-made corpora with sentence reordering annotation exists, at least…”
Argument Mining: A Survey (2020, methodology): “The Argument Annotated Essays Corpus (AAEC), presented in Stab and Gurevych (2014a) and updated in Stab and Gurevych (2017), consists of argument-annotated persuasive essays, and features topic and stance identification, annotation of argument components, and argumentative relations.”
Argumentative Relation Classification as Plausibility Ranking (2019, methodology): “-att. majority 47.8 - - - SVM (Stab and Gurevych, 2017; Opitz and Frank, 2019b) On one hand, this means that the new discourse conﬁguration is still discriminative (either supporting or attacking).”
Let’s Make Your Request More Persuasive: Modeling Persuasive Strategies via Semi-Supervised Neural Nets on Crowdfunding Platforms (2019, background): “Computational argumentation has received much recent attention (Ghosh et al., 2016; Stab and Gurevych, 2017; Peldszus and Stede, 2013; Stab et al., 2018; Ghosh et al., 2014).”
Cross-topic Argument Mining from Heterogeneous Sources (2018, methodology): “We use a logistic regression model with lower-cased unigram features as baseline, which has been shown to be a strong baseline for various other AM task (Daxenberger et al., 2017; Stab and Gurevych, 2017).”
Concatenated Power Mean Word Embeddings as Universal Cross-Lingual Sentence Representations (2018, methodology): “Since their selection of tasks is slightly biased towards sentiment analysis, we add three further tasks: AM , an argumentation mining task based on Stab and Gurevych (2017) where sentences are classiﬁed into the categories major claim, claim, premise, and non-argumentative; AC , a further…”