Language Technology Lab

Marie Bexte
PhD Candidate
marie.bexte@fernuni-hagen.de
0000-0002-7329-2548
mariebexte

Universitätsstraße 27 – PRG / Building 5, Room A 107, 58097 Hagen

As a research assistant in computational linguistics, I focus on the automated evaluation of image-based tasks.

CV

Research Assistant at the research professorship “Computational Linguistics” (since April 2022)
Research Assistant at the “Language Technology Lab” at the University of Duisburg-Essen (March 2021 – March 2022)
MSc Applied Cognitive and Media Science (Cognition and Artifical Intelligence) (2021)
BSc Applied Cognitive and Media Science (2018)

Publications

2022

Similarity-Based Content Scoring - How to Make S-BERT Keep Up With BERT

Bexte, Marie, Horbach, Andrea, and Zesch, Torsten

In Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022) Jul 2022

Abstract PDF

The dominating paradigm for content scoring is to learn an instance-based model, i.e. to use lexical features derived from the learner answers themselves. An alternative approach that receives much less attention is however to learn a similarity-based model. We introduce an architecture that efficiently learns a similarity model and find that results on the standard ASAP dataset are on par with a BERT-based classification approach.
Don’t Drop the Topic - The Role of the Prompt in Argument Identification in Student Writing

Ding, Yuning, Bexte, Marie, and Horbach, Andrea

In Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022) Jul 2022

Abstract PDF

In this paper, we explore the role of topic information in student essays from an argument mining perspective. We cluster a recently released corpus through topic modeling into prompts and train argument identification models on different data settings. Results show that, given the same amount of training data, prompt-specific training performs better than cross-prompt training. However, the advantage can be overcome by introducing large amounts of cross-prompt training data.
LeSpell - A Multi-Lingual Benchmark Corpus of Spelling Errors to Develop Spellchecking Methods for Learner Language

Bexte, Marie, Laarmann-Quante, Ronja, Horbach, Andrea, and Zesch, Torsten

In Proceedings of the Language Resources and Evaluation Conference Jun 2022

Abstract PDF

Spellchecking text written by language learners is especially challenging because errors made by learners differ both quantitatively and qualitatively from errors made by already proficient learners. We introduce LeSpell, a multi-lingual (English, German, Italian, and Czech) evaluation data set of spelling mistakes in context that we compiled from seven underlying learner corpora. Our experiments show that existing spellcheckers do not work well with learner data. Thus, we introduce a highly customizable spellchecking component for the DKPro architecture, which improves performance in many settings.

2021

Implicit Phenomena in Short-answer Scoring Data

Bexte, Marie, Horbach, Andrea, and Zesch, Torsten

In Proceedings of the First Workshop on Understanding Implicit and Underspecified Language Jun 2021

PDF

2020

Appropriateness and Pedagogic Usefulness of Reading Comprehension Questions

Horbach, Andrea, Aldabe, Itziar, Bexte, Marie, Lacalle, Oier, and Maritxalar, Montse

In Proceedings of the 12th International Conference on Language Resources and Evaluation (LREC-2020) Jun 2020

PDF

2018

Corpus of Aspect-based Sentiment in Political Debates

Gold, Darina, Bexte, Marie, and Zesch, Torsten

In KONVENS Jun 2018