Christoph Rensing
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Christoph Rensing has a total of 136 co-authors. Here are the top co-authors by number of shared publications:
Ralf Steinmetz
TU Darmstadt, Darmstadt, Germany
31 shared publicationsLasse Lehmann
Technische Universität Darmstadt
9 shared publicationsRenato Domínguez García
Technische Universität Darmstadt, Darmstadt, Germany
9 shared publicationsTomas Hildebrandt
Multimedia Communications Lab - KOM, TU Darmstadt, Germany
8 shared publicationsPhilipp Scholl
Multimedia Communications Lab - Technische Universität Darmstadt
7 shared publications- Stephan Fischer
Technische Universität Darmstadt
7 shared publications
Latest Publications
- 9 June 2020
- Vol. 12163, 177-190
Fooling Automatic Short Answer Grading Systems
With the rising success of adversarial attacks on many NLP tasks, systems which actually operate in an adversarial scenario need to be reevaluated. For this purpose, we pose the following research question: How difficult is it to fool automatic short answer grading systems? In particular, we investigate the robustness of the state of the art automatic short answer grading system proposed by Sung et al. towards cheating in the form of universal adversarial trigger employment. These are short token sequences that can be prepended to students’ answers in an exam to artificially improve their automatically assigned grade. Such triggers are especially critical as they can easily be used by anyone once they are found. In our experiments, we discovered triggers which allow students to pass exams with passing thresholds of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$50\%$$\end{document}50% without answering a single question correctly. Furthermore, we show that such triggers generalize across models and datasets in this scenario, nullifying the defense strategy of keeping grading models or data secret.- 9 June 2020
- Vol. 12163, 177-190
Fooling Automatic Short Answer Grading Systems
With the rising success of adversarial attacks on many NLP tasks, systems which actually operate in an adversarial scenario need to be reevaluated. For this purpose, we pose the following research question: How difficult is it to fool automatic short answer grading systems? In particular, we investigate the robustness of the state of the art automatic short answer grading system proposed by Sung et al. towards cheating in the form of universal adversarial trigger employment. These are short token sequences that can be prepended to students’ answers in an exam to artificially improve their automatically assigned grade. Such triggers are especially critical as they can easily be used by anyone once they are found. In our experiments, we discovered triggers which allow students to pass exams with passing thresholds of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$50\%$$\end{document}50% without answering a single question correctly. Furthermore, we show that such triggers generalize across models and datasets in this scenario, nullifying the defense strategy of keeping grading models or data secret.- 9 June 2020
- Vol. 12163, 512-523
Remember the Facts? Investigating Answer-Aware Neural Question Generation for Text Comprehension
Reading is a crucial skill in the 21st century. Thus, scaffolding text comprehension by automatically generated questions may greatly profit learners. Yet, the state-of-the-art methods for automatic question generation, answer-aware neural question generators (NQGs), are rarely seen in the educational domain. Hence, we investigate the quality of questions generated by a novel approach comprising an answer-aware NQG and two novel answer candidate selection strategies based on semantic graph matching. In median, the approach generates clear, answerable and useful factual questions outperforming an answer-unaware NQG on educational datasets as shown by automatic and human evaluation. Furthermore, we analyze the types of questions generated, showing that the question types differ across answer selection strategies yet remain factual.
- 9 June 2020
- Vol. 12163, 512-523
Remember the Facts? Investigating Answer-Aware Neural Question Generation for Text Comprehension
Reading is a crucial skill in the 21st century. Thus, scaffolding text comprehension by automatically generated questions may greatly profit learners. Yet, the state-of-the-art methods for automatic question generation, answer-aware neural question generators (NQGs), are rarely seen in the educational domain. Hence, we investigate the quality of questions generated by a novel approach comprising an answer-aware NQG and two novel answer candidate selection strategies based on semantic graph matching. In median, the approach generates clear, answerable and useful factual questions outperforming an answer-unaware NQG on educational datasets as shown by automatic and human evaluation. Furthermore, we analyze the types of questions generated, showing that the question types differ across answer selection strategies yet remain factual.
- 30 April 2020
- Published by Springer Nature
- p. 175-192
Personalized Citation Recommendation Using an Ensemble Model of DSSM and Bibliographic Information
- 30 April 2020
- Published by Springer Nature
- p. 175-192
Personalized Citation Recommendation Using an Ensemble Model of DSSM and Bibliographic Information
- 18 November 2019
- Published by Springer Nature
- p. 107-125
Results of a Survey About the Perceived Task Similarities in Micro Task Crowdsourcing Systems
- 18 November 2019
- Published by Springer Nature
- p. 107-125
Results of a Survey About the Perceived Task Similarities in Micro Task Crowdsourcing Systems
- 9 September 2019
- Published by Springer Nature
- p. 335-348
Automatic Text Difficulty Estimation Using Embeddings and Neural Networks
- 9 September 2019
- Published by Springer Nature
- p. 335-348
Automatic Text Difficulty Estimation Using Embeddings and Neural Networks
- Open Access
- 8 April 2019
- Published by Association for Computing Machinery (ACM)
- p. 1683-1686
Preselection of documents for personalized recommendations of job postings based on word embeddings
- 8 April 2019
- Published by Association for Computing Machinery (ACM)
- p. 1683-1686
Open AccessPreselection of documents for personalized recommendations of job postings based on word embeddings
- 14 August 2018
- Published by Springer Nature
- p. 609-612
Ensuring Novelty and Transparency in Learning Resource-Recommendation Based on Deep Learning Techniques
- 14 August 2018
- Published by Springer Nature
- p. 609-612
Ensuring Novelty and Transparency in Learning Resource-Recommendation Based on Deep Learning Techniques
- 22 May 2018
- Published by Springer Nature
- p. 389-396
Towards Ontology-Based Training-Less Multi-label Text Classification
- 22 May 2018
- Published by Springer Nature
- p. 389-396
Towards Ontology-Based Training-Less Multi-label Text Classification