• Publications
  • Influence
Neural End-to-End Learning for Computational Argumentation Mining
TLDR
We investigate neural techniques for end-to-end computational argumentation mining (AM). Expand
  • 84
  • 11
  • PDF
Turbulent Stability of Emergent Roles: The Dualistic Nature of Self-Organizing Knowledge Coproduction
TLDR
We investigate the temporal dynamics underlying emergent roles on individual and organizational levels. Expand
  • 43
  • 5
  • PDF
What is the Essence of a Claim? Cross-Domain Claim Identification
TLDR
We perform a qualitative analysis across six different datasets and show that these appear to conceptualize claims quite differently. Expand
  • 39
  • 5
  • PDF
Automatically Classifying Edit Categories in Wikipedia Revisions
TLDR
We present the results from an automatic classification experiment, based on an annotated corpus of edits in the English Wikipedia. Expand
  • 42
  • 5
  • PDF
Classification and Clustering of Arguments with Contextualized Word Embeddings
TLDR
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. Expand
  • 39
  • 4
  • PDF
A Corpus-Based Study of Edit Categories in Featured and Non-Featured Wikipedia Articles
TLDR
We propose a 21-category classification scheme for edits based on Faigley and Witte’s (1981) model. Expand
  • 33
  • 4
  • PDF
On the "How" and "Why" of Emergent Role Behaviors in Wikipedia
TLDR
We identify four categories of temporal role-taking behaviors, that differ in their mobility between emergent roles and across Wikipedia articles. Expand
  • 26
  • 4
  • PDF
ArgumenText: Searching for Arguments in Heterogeneous Sources
TLDR
We present ArgumenText, which we believe is the first system for topic-relevant argument search in heterogeneous texts. Expand
  • 49
  • 3
  • PDF
UKP TU-DA at GermEval 2017: Deep Learning for Aspect Based Sentiment Detection
TLDR
This paper describes our submissions to the GermEval 2017 Shared Task, which focused on the analysis of customer feedback about the Deutsche Bahn AG. Expand
  • 7
  • 3
DKPro TC: A Java-based Framework for Supervised Learning Experiments on Textual Data
TLDR
We present DKPro TC, a framework for supervised learning experiments on textual data. Expand
  • 61
  • 2
  • PDF