We investigate neural techniques for endto-end computational argumentation mining (AM). We frame AM both as a tokenbased dependency parsing and as a tokenbased sequence tagging problem, including a multi-task learning setup. Contrary to models that operate on the argument component level, we find that framing AM as dependency parsing leads to subpar performance results. In contrast, less complex (local) tagging models based on BiLSTMs perform robustly across classification scenarios, being able to catch longrange dependencies inherent to the AM problem. Moreover, we find that jointly learning 'natural' subtasks, in a multi-task learning setup, improves performance.

We experiment with two recent contextualized word embedding methods (ELMo and BERT) in the context of open-domain argument search. For the first time, we show how to leverage the power of contextualized word embeddings to classify and cluster topic-dependent arguments, achieving impressive results on both tasks and across multiple datasets. For argument classification, we improve the state-of-the-art for the UKP Sentential Argument Mining Corpus by 20.8 percentage points and for the IBM Debater -Evidence Sentences dataset by 7.4 percentage points. For the understudied task of argument clustering, we propose a pre-training step which improves by 7.8 percentage points over strong baselines on a novel dataset, and by 12.3 percentage points for the Argument Facet Similarity (AFS) Corpus. 1 Contextualized word embeddings, especially ELMo (Peters et al., 2018) and BERT (Devlin et al., 2018) could offer a viable solution to this problem. In contrast to traditional word embeddings like word2vec (Mikolov et al., 2013) or

We investigate whether and where multitask learning (MTL) can improve performance on NLP problems related to argumentation mining (AM), in particular argument component identification. Our results show that MTL performs particularly well (and better than single-task learning) when little training data is available for the main task, a common scenario in AM. Our findings challenge previous assumptions that conceptualizations across AM datasets are divergent and that MTL is difficult for semantic or higher-level tasks.

Increasingly, new forms of organizing for knowledge production are built around self-organizing coproduction community models with ambiguous role definitions. Current theories struggle to explain how high-quality knowledge is developed in these settings and how participants self-organize in the absence of role definitions, traditional organizational controls, or formal coordination mechanisms. In this article, we engage the puzzle by investigating the temporal dynamics underlying emergent roles on individual and organizational levels. Comprised of a multilevel large-scale empirical study of Wikipedia stretching over a decade, our study investigates emergent roles in terms of prototypical activity patterns that organically emerge from individuals’ knowledge production actions. Employing a stratified sample of 1,000 Wikipedia articles, we tracked 200,000 distinct participants and 700,000 coproduction activities, and recorded each activity’s type. We found that participants’ role-taking behavior is turbulent across roles, with substantial flow in and out of coproduction work. Our findings at the organizational level, however, show that work is organized around a highly stable set of emergent roles, despite the absence of traditional stabilizing mechanisms such as predefined work procedures or role expectations. This dualism in emergent work is conceptualized as “turbulent stability.” We attribute the stabilizing factor to the artifact-centric production process and present evidence to illustrate the mutual adjustment of role taking according to the artifact’s needs and stage. We discuss the importance of the affordances of Wikipedia in enabling such tacit coordination. This study advances our theoretical understanding of the nature of emergent roles and self-organizing knowledge coproduction. We discuss the implications for custodians of online communities as well as for managers of firms engaging in self-organized knowledge collaboration.

Argument mining is a core technology for enabling argument search in large corpora. However, most current approaches fall short when applied to heterogeneous texts. In this paper, we present an argument retrieval system capable of retrieving sentential arguments for any given controversial topic. By analyzing the highest-ranked results extracted from Web sources, we found that our system covers 89% of arguments found in expert-curated lists of arguments from an online debate portal, and also identifies additional valid arguments.