Research
Publications
A large part of my research revolves around multimodal language generation, especially Referring Expression Generation.
However, in collaboration with other researchers, I have also published on other topics in natural language processing / generation, e.g. explanation generation, probing language models and distributed word representations with psychological tests of lexical retrieval, and visual language grounding.
(Also see Google Scholar, ORCID, Semantic Scholar)
2024
- Sieker, Judith, Simeon Junker, Ronja Utescher, Nazia Attari, Heiko Wersing, Hendrik Buschmeier and Sina Zarrieß. 2024. The Illusion of Competence: Evaluating the Effect of Explanations on Users' Mental Models of Visual Question Answering Systems. To appear in: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024).
- Junker, Simeon and Sina Zarrieß. 2024. Resilience through Scene Context in Visual Referring Expression Generation. Association for Computational Linguistics: Proceedings of the 17th International Conference on Natural Language Generation (INLG 2024). BEST PAPER AWARD. [CODE] [SLIDES]
2023
- Schüz, Simeon and Sina Zarrieß. 2023. Keeping an Eye on Context: Attention Allocation over Input Partitions in Referring Expression Generation. Association for Computational Linguistics: Proceedings of the Workshop on Multimodal, Multilingual Natural Language Generation and Multilingual WebNLG Challenge (MM-NLG 2023). [CODE]
- Schüz, Simeon, Albert Gatt and Sina Zarrieß. 2023. Rethinking symbolic and visual context in Referring Expression Generation. Frontiers in Artificial Intelligence (6).
2022
- Alacam, Özge, Simeon Schüz, Martin Wegrzyn, Johanna Kißler and Sina Zarrieß. 2022. Exploring Semantic Spaces for Detecting Clustering and Switching in Verbal Fluency. Association for Computational Linguistics: Proceedings of the 29th International Conference on Computational Linguistics (COLING 2022).
2021
- Schüz, Simeon and Sina Zarrieß. 2021. Decoupling Pragmatics: Discriminative Decoding for Referring Expression Generation. Association for Computational Linguistics: Proceedings of the Reasoning and Interaction Conference (ReInAct 2021). [CODE]
- Zarrieß, Sina, Hendrik Buschmeier, Ting Han and Simeon Schüz. 2021. Decoding, Fast and Slow: A Case Study on Balancing Trade-Offs in Incremental, Character-level Pragmatic Reasoning. Association for Computational Linguistics: Proceedings of the 14th International Conference on Natural Language Generation (INLG 2021). [CODE]
- Zarrieß, Sina, Henrik Voigt and Simeon Schüz. 2021. Decoding Methods in Neural Language Generation: A Survey. Information 12(9), 355.
- Schüz, Simeon, Ting Han and Sina Zarrieß. 2021. Diversity as a By-Product: Goal-oriented Language Generation Leads to Linguistic Variation. Association for Computational Linguistics: Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL 2021). [CODE]
2020
- Schüz, Simeon and Sina Zarrieß. 2020. Knowledge Supports Visual Language Grounding: A Case Study on Colour Terms. Association for Computational Linguistics: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020).[CODE]
- Schüz, Simeon and Sina Zarrieß. 2020. Contextual Knowledge in Visual Language Grounding: Using Object-Specific Information for Colour Naming. Poster at the GeCKo symposium.