PUBLICATIONS

How Well Can Masked Language Models Spot Identifiers That Violate Naming Guidelines?

Viola Campos, Johannes Villmow, Jean Petry, Amine Abbad-Andaloussi, Adrian Ulges, and Barbara Weber | SCAM 2023 PDF

Addressing Leakage in Self-Supervised Contextualized Code Retrieval

Johannes Villmow, Viola Campos, Adrian Ulges, Ulrich Schwanecke | COLING 2022 PDF

SELECTED WORK

Unsupervised Neural Text Search using Retrieval-Augmented Language Modeling

Master thesis. Inspired by recent retrieval-augmented language models such as REALM or RAG, the work investigates possibilities of using retrieval-augmented language modeling for self-supervised training of a transformer-based retriever. [ PDF ]