Anja Reusch


2023

pdf
Mr-Fosdick at SemEval-2023 Task 5: Comparing Dataset Expansion Techniques for Non-Transformer and Transformer Models: Improving Model Performance through Data Augmentation
Christian Falkenberg | Erik Schönwälder | Tom Rietzke | Chris-Andris Görner | Robert Walther | Julius Gonsior | Anja Reusch
Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)

In supervised learning, a significant amount of data is essential. To achieve this, we generated and evaluated datasets based on a provided dataset using transformer and non-transformer models. By utilizing these generated datasets during the training of new models, we attain a higher balanced accuracy during validation compared to using only the original dataset.

pdf
Sabrina Spellman at SemEval-2023 Task 5: Discover the Shocking Truth Behind this Composite Approach to Clickbait Spoiling!
Simon Birkenheuer | Jonathan Drechsel | Paul Justen | Jimmy Phlmann | Julius Gonsior | Anja Reusch
Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)

This paper describes an approach to automat- ically close the knowledge gap of Clickbait- Posts via a transformer model trained for Question-Answering, augmented by a task- specific post-processing step. This was part of the SemEval 2023 Clickbait shared task (Frbe et al., 2023a) - specifically task 2. We devised strategies to improve the existing model to fit the task better, e.g. with different special mod- els and a post-processor tailored to different inherent challenges of the task. Furthermore, we explored the possibility of expanding the original training data by using strategies from Heuristic Labeling and Semi-Supervised Learn- ing. With those adjustments, we were able to improve the baseline by 9.8 percentage points to a BLEU-4 score of 48.0%.

2022

pdf
Extracting Operator Trees from Model Embeddings
Anja Reusch | Wolfgang Lehner
Proceedings of the 1st Workshop on Mathematical Natural Language Processing (MathNLP)

Transformer-based language models are able to capture several linguistic properties such as hierarchical structures like dependency or constituency trees. Whether similar structures for mathematics are extractable from language models has not yet been explored. This work aims to probe current state-of-the-art models for the extractability of Operator Trees from their contextualized embeddings using the structure probe designed by Hewitt and Manning. We release the code and our data set for future analysis.