I’m a PhD candidate at UniMelb, very fortunate to be advised by Lea Frermann and Tim Baldwin. My thesis focuses on exploring ways to automatically find biases in the narrative of news articles. I consider myself a computational linguist, who likes to dance, read and discuss about general things. I love the idea of combining languages and computer science, therefore NLP is one of my passions.

Work experience

My (current) main interest is fairness in news data. But I like to keep an eye in many other topics like: automatic fact checking (afc), question answering, generation. Dialogue systems will be probably my first love for ever.

Before my PhD, I worked as a researcher in the UKP Lab at the TU Darmstadt. Prior to that, I was a machine learning consultant at Novatec GmbH, a company with headquarters in Leinfelden Germany. There, I worked on prototyping solutions for different clients and helping with the design of workshops and lectures about machine learning. Previous to that I interned for several companies, including Mercedes Benz in Germany and in CA, USA, Sony Deutschland GmbH and Compart AG in Böblingen Germany. For more details see my cv here.

News

• Oct, 2022, I'm officially a PhD candidate! 🎉
• Oct, 2021, I started my PhD at UniMelb 😎
• Jul, 2019, attended LxMLS 2019 as tutor!
• Jun, 2019, attended Google NLP Summit.
• Apr, 2019, We got a paper accepted at AIED 2019.
• Feb, 2019, Our paper got accepted at ICASSP 2019.
• Jan, 2019, We won (Team PIG from UKP Lab) the first place at the Data Science Society Datathon Hack the news.
• June 14-21, 2018, got accepted as tutor for LxMLS 2018!
• July 20-27, 2017, attended the most enjoyable machine learning summer school (LxMLS).

Service

• Co-Chair at SRW ACL 2023 with Vishakh Padmakumar and Yao Fu
• Zoom Chair at EACL 2021
• Zoom Co-Chair at EMNLP 2020

Publications

• Connecting the Dots in News Analysis: Bridging the Cross-Disciplinary Disparities in Media Bias and Framing, Gisela Vallejo, Timothy Baldwin, Lea Frermann. In Proceedings of the Sixth Workshop on Natural Language Processing and Computational Social Science (NLP+CSS), Mexico City, Mexico. Association for Computational Linguistics,(presented at NAACL), 2024.
• AMBIFC: Fact-Checking Ambiguous Claims with Evidence, Max Glockner, Ieva Staliūnaitė, James Thorne, Gisela Vallejo, Andreas Vlachos, Iryna Gurevych. In: Transactions of the Association for Computational Linguistics (TACL),(presented at EMNLP), 2023.
• Evaluating the Examiner: The Perils of Pearson Correlation for Validating Text Similarity Metrics, Gisela Vallejo, Timothy Baldwin, Lea Frermann. In Proceedings of The 20th Annual Workshop of the Australasian Language Technology Association (ALTA), December 2022.
• An Annotation Protocol for Collecting User-Generated Counter-Arguments using Crowdsourcing, Paul Reisert, Gisela Vallejo, Naoya Inoue, Iryna Gurevych, and Kentaro Inui. In Proceedings of the 20th International Conference on Artificial Intelligence in Education (AIED), June 2019.
• Context-aware Neural-based Dialog Act Classification on Automatically Generated Transcriptions, Daniel Ortega, Chia-Yu Li, Gisela Vallejo, Pavel Denisov, Thang Vu. In Proceedings of International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019.
• One Model, Different Languages: Twitter Emotion Classification using Distant Supervision, Jan Weßling, Gisela Vallejo. In Proceedings of Tagung der Computerlinguistik Studierenden (TaCoS), 2017.