• Publications
  • Influence
UBY - A Large-Scale Unified Lexical-Semantic Resource Based on LMF
TLDR
We present Uby, a large-scale lexical-semantic resource combining a wide range of information from expert-constructed and collaboratively constructed resources for English and German. Expand
  • 151
  • 17
  • PDF
MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance
TLDR
A robust evaluation metric has a profound impact on the development of text generation systems. Expand
  • 60
  • 17
  • PDF
A Retrospective Analysis of the Fake News Challenge Stance Detection Task
TLDR
The 2017 Fake News Challenge Stage 1 (FNC-1) shared task addressed a stance classification task as a crucial first step towards detecting fake news. Expand
  • 74
  • 10
  • PDF
What Psycholinguists Know About Chemistry: Aligning Wiktionary and WordNet for Increased Domain Coverage
TLDR
We propose a new automatically aligned resource of Wiktionary and WordNet that has (i) a very high domain coverage of word senses and (ii) an enriched sense representation, including pronunciations, etymologies, translations, etc. Expand
  • 62
  • 5
  • PDF
DKPro Agreement: An Open-Source Java Library for Measuring Inter-Rater Agreement
TLDR
In this paper, we introduce a novel Java implementation of multiple inter-rater agreement measures, which we make available as open-source software. Expand
  • 33
  • 5
  • PDF
To Exhibit is not to Loiter: A Multilingual, Sense-Disambiguated Wiktionary for Measuring Verb Similarity
TLDR
We construct a new multilingual lexical resource from Wiktionary by disambiguating semantic relations and translations. Expand
  • 25
  • 4
  • PDF
Development of an Approach for Analyzing Supply Chain Complexity
Supply chains are faced with a rising complexity of products, structures, and processes. Because of the strong link between a supply chain’s complexity and its efficiency the supply chain complexityExpand
  • 60
  • 3
  • PDF
Better Rewards Yield Better Summaries: Learning to Summarise Without References
TLDR
We learn a reward function from human ratings on 2,500 summaries that can guide RL to generate human-appealing summaries. Expand
  • 17
  • 3
  • PDF
How Web Communities Analyze Human Language: Word Senses in Wiktionary
TLDR
The emergence of Web 2.0 enables new insights in many research areas. Expand
  • 22
  • 3
  • PDF
Bridging the gap between extractive and abstractive summaries: Creation and evaluation of coherent extracts from heterogeneous sources
TLDR
We present a corpus of heterogeneous documents for summarization to address the issue that information seekers usually face a range of different types of information sources. Expand
  • 16
  • 3
  • PDF