Scholar
Afra Feyza Akyürek
Google Scholar ID: RXsYj9IAAAAJ
PhD Student in Computer Science, Boston University
Citations & Impact
Citations
580
H-index
11
i10-index
11
Publications
14
Co-authors
7
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- 1. Published 'Deductive Closure Training of Language Models for Coherence, Accuracy, and Updatability' at Findings of ACL 2024
- 2. Published 'DUnE: Dataset for Unified Editing' at EMNLP 2023
- 3. Published 'RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs' at ACL 2023
- 4. Published 'Subspace Regularizers for Few-Shot Class Incremental Learning' at ICLR 2022
Research Experience
- 1. Collaborated with teams at Allen AI and Apple
- 2. Collaborated with Jacob Andreas at MIT
- 3. Internship experiences: worked on gender bias in language models at Apple, and developed an automatic feedback generator at Allen AI's Aristo team
Education
- 1. Izmir Fen Lisesi, Turkey
- 2. Koc University, double major in Computer Engineering and Industrial Engineering
- 3. Carnegie Mellon University, PhD in Statistics (later transferred to Boston University)
- 4. Boston University, PhD in Computer Science, supervised by Derry Wijaya
Background
- PhD student in Computer Science at Boston University, focusing on natural language processing. Her research interest lies in enhancing language model interactions through natural language feedback to be more akin to human-like communication.
Miscellany
- Comes from a family of avid travelers and tries to keep the spirit alive.
