Portfolio item number 1
Published:
Short description of portfolio item number 1
Posts by Collection
portfolio
Portfolio item number 2
Published:
Short description of portfolio item number 2
publications
Adversarial Training for Aspect-Based Sentiment Analysis with BERT
Published in ICPR, 2020
We propose a novel architecture called BERT Adversarial Training (BAT) to utilize adversarial training for the two major tasks of Aspect Extraction and Aspect Sentiment Classification in sentiment analysis.
AEDA: An Easier Data Augmentation Technique for Text Classification
Published in Findings of EMNLP, 2021
This paper proposes AEDA (An Easier Data Augmentation) technique to help improve the performance on text classification tasks.
Do Multilingual Large Language Models Mitigate Stereotype Bias?
Published in C3NLP Workshop @ ACL, 2024
We investigate the effect of multilingual training on bias mitigation by systematically training six LLMs of identical size (2.6B parameters) and architecture: five monolingual models (English, German, French, Italian, and Spanish) and one multilingual model trained on an equal distribution of data across these languages, all using publicly available data.
ArithmAttack: Evaluating Robustness of LLMs to Noisy Context in Math Problem Solving
Published in LLMSEC Workshop @ ACL, 2025
We propose ArithmAttack to examine how robust the LLMs are when they encounter noisy prompts that contain extra noise in the form of punctuation marks.
Multi-Hop Reasoning for Question Answering with Hyperbolic Representations
Published in Findings of ACL, 2025
Through a simple integration of hyperbolic representations with an encoder-decoder model, we perform a controlled and comprehensive set of experiments to compare the capacity of hyperbolic space versus Euclidean space in multi-hop reasoning.
Label-Consistent Data Generation for Aspect-Based Sentiment Analysis Using LLM Agents
Published in (soon to appear) WASSA @ EACL 2026, 2026
We propose an agentic data augmentation method for Aspect-Based Sentiment Analysis (ABSA) that uses iterative generation and verification to produce high-quality synthetic training examples.
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown file that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Dialog Systems
Undergraduate course, University of Marburg, 2022
Introduction to Natural Language Processing
Undergraduate course, University of Marburg, 2023
Taught the core concepts of NLP, including TF-IDF, word embeddings, RNNs, and Transformers, as well as evaluation methodologies and the applications of NLP methods in various domains such as conversational systems and computational social science.
Dialog Systems
Undergraduate course, University of Bonn, 2024
Taught the main components of a dialog system, e.g., ASR concepts, NLU, dialog manager, dialog state tracking, & NLG, and the tasks involved in each module.
Dialog Systems
Undergraduate course, University of Bonn, 2025
In the lab sessions, I taught the concepts of LLM agents, agentic frameworks such as SmolAgents, LangChain and LlamaIndex, and how to build a personal chatbot using small models, whose quality is improved with them having the capabilities of internet search and tool use.