My interests broadly lie in the fields of natural language processing and explainable AI. I’m currently focused on developing and evaluating models that provide readable explanations of their decision process for tasks requiring advanced reasoning abilities.

I did my PhD in the Heidelberg University NLP Group where I worked on learning with limited labeled data for discourse-oriented tasks. My advisor was Anette Frank. Prior to receiving my PhD in Janurary 2019, I completed B.Sc. (2013) and M.Sc. (2015) in Mathematics at the University of Zagreb.

I grew up in Omiš, Croatia.


June 2021 NLP Highlights Podcast: I talked with Tosin Adewumi and Perez Ogayo about "lowresourcedness" and how Masakhane is using participatory research to spur NLP in African languages.
May 2021 A new episode of NLP Highlights Podcast with Lisa Li about her work on prefix-tuning is live.
May 2021 Three papers accepted to Findings of ACL, about effective attention, linearized graph-to-text generation, and contrastive explanations. Kudos to Kaiser, Alexander, and Alexis! 🙌
May 2021 I joined NLP Highlights Podcast as a co-host! My first episode is with Danna Gurari who joined Pradeep and me to talk about VQA that supports real users. Listen to this episode here.
April 2021 We released a documentation of C4 accompanied with an interactive demo and a github repository.
March 2021 I'm a panelist at the SoCal ML/NLP Symposium.
Feb 2021 We released a review of datasets for explainable NLP accompanied with a website.
Dec 2020 A new preprint on graph awareness in linearized graph-to-text generation is available on arXiv.
Dec 2020 A new preprint on generating contrastive explanations is available on arXiv.
Dec 2020 I'm one of outstanding reviewers for EMNLP 2020.
Dec 2020 A paper on formalization of human-AI trust is accepted to FAccT 2021.
Dec 2020 Updated my website, woo.