Jonas Wallat

Jonas Wallat

PhD Student at L3S Research Center, working on interpretability for NLP models

Publications

Probing BERT for Ranking Abilities

Published in ECIR 2023, 2023

In this paper, we probe BERT-rankers to understand which abilities are acquired by fine-tuning on a ranking task.

Recommended citation: Wallat, Jonas, et al. "Probing BERT for ranking abilities." Advances in Information Retrieval: 45th European Conference on Information Retrieval, ECIR 2023, Dublin, Ireland, April 2–6, 2023, Proceedings, Part II. Cham: Springer Nature Switzerland, 2023. https://link.springer.com/chapter/10.1007/978-3-031-28238-6_17

Explainable Information Retrieval: A Survey

Published in arXiv, 2022

This survey fills a vital gap in the otherwise topically diverse literature of explainable information retrieval. It categorizes and discusses recent explainability methods developed for different application domains in information retrieval, providing a common framework and unifying perspectives.

Recommended citation: Anand, Avishek, et al. "Explainable Information Retrieval: A Survey." arXiv preprint arXiv:2211.02405 (2022). https://arxiv.org/abs/2211.02405

BERTnesia: Investigating the capture and forgetting of knowledge in BERT

Published in BLACKBOXNLP 2020, 2020

In this paper, we probe BERT specifically to understand and measure the relational knowledge it captures.

Recommended citation: Wallat, Jonas et al. “BERTnesia: Investigating the capture and forgetting of knowledge in BERT.” BLACKBOXNLP (2020). https://www.semanticscholar.org/paper/BERTnesia%3A-Investigating-the-capture-and-forgetting-Wallat-Singh/616610e0b0a31ab4bac1c64fd0b65c2572185522#paper-header