• Publications
  • Influence
Generating Coherent Summaries of Scientific Articles Using Coherence Patterns
Previous work on automatic summarization does not thoroughly consider coherence while generating the summary. We introduce a graph-based approach to summarize scientific articles. We employ coherenceExpand
  • 27
  • 4
  • PDF
Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systems
TLDR
We investigate the impact of visual adversarial attacks on current NLP systems on character-, word-, and sentence-level tasks, showing that both neural and non-neural models are, in contrast to humans, extremely sensitive to such attacks, suffering performance decreases of up to 82\%. Expand
  • 25
  • 2
  • PDF
A Neural Local Coherence Model for Text Quality Assessment
TLDR
This author is currently employed by the Ubiquitous Knowledge Processing (UKP) Lab, Technische Universität Darmstadt. Expand
  • 29
  • PDF
Graph-based Coherence Modeling For Assessing Readability
TLDR
We introduce novel graph-based coherence features based on frequent subgraphs and compare their ability to assess the readability of Wall Street Journal articles. Expand
  • 23
  • PDF
Dynamic Performance Analysis and Simulation of a Full Scale Activated Sludge System Treating an Industrial Wastewater Using Artificial Neural Network
Due to changeable nature of the industrial wastewaters, proper operation of an industrial wastewater treatment plant is of prior importance in order to keep the process stability at the desiredExpand
  • 9
  • PDF
Lexical Coherence Graph Modeling Using Word Embeddings
TLDR
We introduce the lexical coherence graph (LCG), a new graph-based model to represent lexical relations among sentences. Expand
  • 10
  • PDF
Reward Learning for Efficient Reinforcement Learning in Extractive Document Summarisation
TLDR
We propose RELIS, a novel RL paradigm that learns a reward function with Learning-to-Rank (L2R) algorithms at training time and uses this reward function to train an input-specific RL policy at test time. Expand
  • 8
  • PDF
Normalized Entity Graph for Computing Local Coherence
TLDR
Guinaudeau and Strube introduce a graph based model to compute local entity coherence. Expand
  • 6
  • PDF
Effect of biomass concentration and aeration rate on performance of a full-scale industrial estate wastewater treatment plant
Abstract In this study, performance of an industrial estate wastewater treatment plant (WWTP) (Faraman's Industrial Estate, Kermanshah, Iran) was investigated by varying effective operating variablesExpand
  • 3
Using a Graph-based Coherence Model in Document-Level Machine Translation
TLDR
We integrate the graph-based coherence model proposed by Mesgar and Strube, (2016) with Docent (Hardmeier et al., 2012, Hardmeier, 2014) a document-level machine translation system. Expand
  • 4
  • PDF