Welcome to my GitHub! I’m Diana, a passionate Computational Linguist diving deep into the realms of NLP and AI. Here's where I break down language barriers and build bridges with code.
🖥️ I’m currently working as a computational linguist.
🎥 I'm also a content creator, focusing on computational linguistics topics in the era of AI.
🌱 My current research interest is in fact-checking within large language models (LLMs).
🛠️ My Tactic: Divide and conquer – I tackle complex language problems by breaking them down into manageable pieces.
🎓 Explore my academic work and publications: My Google Scholar
👯 I’m open to collaborate on:
- Fact-checking
- Low-resource languages in NLP
- Interpretability and Explanaibility of AI
- Sexist and Offensive Language Detection
- Corpus Creation
- Innovative AI Applications in Language Processing
💬 Ask me about:
- CoRoSeOf - An Annotated Corpus of Romanian Sexist and Offensive Tweets
- UD_Romanian-TueCL - A UD annotated treebank corpus extracted from Coroseof
- RoFact - a Romanian fact-checking dataset (789 claims), with multilingual/LLM baselines.
- The nitty-gritty of computational linguistics and natural language processing.
- Strategies for fact-checking, sexist and offensive language detection in text, corpus creation, and annotation.
- How AI is reshaping the landscape of language models.
📫 How to reach me:
- 📧 Email me at diana.hoefels@gmail.com
- 🤝 Connect with me on LinkedIn
😄 Convo Starter: Always here for a good chat about language, AI, or anything tech!
⚡ Fun fact: I built CoRoSeOf, a dataset aimed at training AI to recognize and address sexism in text. I believe in using the power of words for good!
👋 Thanks for stopping by!