49 citations · 66 across the 14 of their papers we have counts for
16 papers
Probing Chemical Language Models: Effects of Pre-training and Fine-tuning
Anna Karnysheva, Dietrich Klakow, Ji-Ung Lee
Chemical language models (CLMs) are trained with linearized representations such as SMILES, yet it remains unclear which chemically meaningful substructures they encode. To foster…
Fork-Think with Confidence
Zena Al-Khalili, Rafi Hakim, Dietrich Klakow +1
Parallel thinking has enjoyed great success for boosting LLM performance on reasoning tasks without the need for any re-training. However, existing methods follow a think-first-the…
AuthorMix: Modular Authorship Style Transfer via Layer-wise Adapter Mixing
Sarubi Thillainathan, Ji-Ung Lee, Michael Sullivan +1
The task of authorship style transfer involves rewriting text in the style of a target author while preserving the meaning of the original text. Existing style transfer methods tra…
Bridging Fairness and Explainability: Can Input-Based Explanations Promote Fairness in Hate Speech Detection?
Yifan Wang, Mayank Jobanputra, Ji-Ung Lee +3
Natural language processing (NLP) models often replicate or amplify social bias from training data, raising concerns about fairness. At the same time, their black-box nature makes…
B-cos LM: Efficiently Transforming Pre-trained Language Models for Improved Explainability
Yifan Wang, Sukrut Rao, Ji-Ung Lee +2
Post-hoc explanation methods for black-box models often struggle with faithfulness and human interpretability due to the lack of explainability in current neural architectures. Mea…
Constrained C-Test Generation via Mixed-Integer Programming
Ji-Ung Lee, Marc E. Pfetsch, Iryna Gurevych
This work proposes a novel method to generate C-Tests; a deviated form of cloze tests (a gap filling exercise) where only the last part of a word is turned into a gap. In contrast…
Surveying (Dis)Parities and Concerns of Compute Hungry NLP Research
Ji-Ung Lee, Haritz Puerto, Betty van Aken +8
Many recent improvements in NLP stem from the development and use of large pre-trained language models (PLMs) with billions of parameters. Large model sizes makes computational cos…
Rediscovering Hashed Random Projections for Efficient Quantization of Contextualized Sentence Embeddings
Ulf A. Hamster, Ji-Ung Lee, Alexander Geyken +1
Training and inference on edge devices often requires an efficient setup due to computational limitations. While pre-computing data representations and caching them on a server can…
Lessons Learned from a Citizen Science Project for Natural Language Processing
Jan-Christoph Klie, Ji-Ung Lee, Kevin Stowe +6
Many Natural Language Processing (NLP) systems use annotated corpora for training and evaluation. However, labeled data is often costly to obtain and scaling annotation projects is…
Efficient Methods for Natural Language Processing: A Survey
Marcos Treviso, Ji-Ung Lee, Tianchu Ji +19
Recent work in natural language processing (NLP) has yielded appealing results from scaling model parameters and training data; however, using only scale to improve performance mea…
Transformers with Learnable Activation Functions
Haishuo Fang, Ji-Ung Lee, Nafise Sadat Moosavi +1
Activation functions can have a significant impact on reducing the topological complexity of input data and therefore improve the performance of the model. Selecting a suitable act…
TexPrax: A Messaging Application for Ethical, Real-time Data Collection and Annotation
Lorenz Stangier, Ji-Ung Lee, Yuxi Wang +4
Collecting and annotating task-oriented dialog data is difficult, especially for highly specific domains that require expert knowledge. At the same time, informal communication cha…
Investigating label suggestions for opinion mining in German Covid-19 social media
Tilman Beck, Ji-Ung Lee, Christina Viehmann +3
This work investigates the use of interactively updated label suggestions to improve upon the efficiency of gathering annotations on the task of opinion mining in German Covid-19 s…
Empowering Active Learning to Jointly Optimize System and User Demands
Ji-Ung Lee, Christian M. Meyer, Iryna Gurevych
Existing approaches to active learning maximize the system performance by sampling unlabeled instances for annotation that yield the most efficient training. However, when active l…
Manipulating the Difficulty of C-Tests
Ji-Ung Lee, Erik Schwan, Christian M. Meyer
We propose two novel manipulation strategies for increasing and decreasing the difficulty of C-tests automatically. This is a crucial step towards generating learner-adaptive exerc…
Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systems
Steffen Eger, Gözde Gül Şahin, Andreas Rücklé +6
Visual modifications to text are often used to obfuscate offensive comments in social media (e.g., "!d10t") or as a writing style ("1337" in "leet speak"), among other scenarios. W…