🧑‍🔬 Sina Zarrieß

🏛️ Affiliations

🎓Bielefeld UniversityBielefeld · Germany2015–2026 · 109 papersEmploymentcurrent🎓University of StuttgartStuttgart · Germany2010–2013 · 10 papers🎓University of PotsdamPotsdam · Germany2006–2010 · 4 papers🎓Friedrich Schiller University JenaJena · Germany2020–2021 · 3 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

🧭 Topics

🧠 Language models & pretraining (3)🧒 Psycholinguistics & language acquisition (3)😉 Implicature (2)🧷 Idioms & multiword expressions (2)✍️ Text generation (1)📏 Evaluation & benchmarks (1)🔬 Interpretability (1)

📅 Works by year

2020s

2010s

📄 Papers

The most cited first (OpenAlex and our library).

1. Know What You Don't Know: Modeling a Pragmatic Speaker that Refers to Objects of Unknown Categories (2019 · 24 citations)
   A speaker must refer to an object in an image whose category the speaker does not know, for example a bus when only cars were seen in training.
2. Generating Non-Projective Word Order in Statistical Linearization (2012 · 23 citations)
   A projective linearizer can only produce word orders in which no two edges cross, and many languages need crossings.
3. Underspecifying and Predicting Voice for Surface Realisation Ranking (2011 · 11 citations)
   The authors regenerate German corpus sentences with a reversible LFG grammar and a ranker that chooses among the candidate realisations.
4. When Your Language Model Cannot Even Do Determiners Right: Probing for Anti-Presuppositions and the Maximize Presupposition! Principle (2023 · 9 citations)
   The paper asks whether masked language models follow the Maximize Presupposition! principle (MP!), which says a speaker should use the presuppositionally stronger of two alternatives when both are true: "the" over "a" when there is exactly one item, and "both" over "all" for two items.
5. Are BabyLMs Deaf to Gricean Maxims? A Pragmatic Evaluation of Sample-efficient Language Models (2025 · 4 citations)
   The authors test whether language models trained on small amounts of data (BabyLM) can detect violations of Grice's conversational maxims.
6. Surprisal and Metaphor Novelty Judgments: Moderate Correlations and Divergent Scaling Effects Revealed by Corpus-Based and Synthetic Datasets (2026 · 1 citation)
   The paper asks whether surprisal from language models can serve as a measure of how novel a metaphor is. Separating creative metaphors from conventionalized ones is difficult even for human annotators. The authors computed surprisal on metaphor-related words with 16 causal LM variants of different sizes, including…
7. Child-directed speech facilitates production, not comprehension, in BabyLMs (2026)
   Previous studies of BabyLM models, that is, language models trained on an amount of data comparable to a child's experience, have mostly found no benefit from child-directed speech (CDS).
8. The Frequency Confound in Language-Model Surprisal and Metaphor Novelty (2026)
   Researchers often treat language-model surprisal as a measure of how predictable a word is in context, and earlier work found that it tracks human judgments of metaphor novelty.

Also in our library

15 more works of theirs are in our library without a page here yet; they will appear as we publish them.

🤝 Co-authors here

9 co-authors with a page, the most papers together first.

• Jonas Kuhn ×2
• Judith Sieker ×2
• Omar Momen ×2
• Anders Björkelund
• Aoife Cahill
• Bastian Bunzeck
• Bernd Bohnet
• David Schlangen
• Wolfgang Seeker

🔗 Cited by

Papers of our library cite their works 68 times (of the 140,884 papers whose bibliographies we read); 13 citing papers with a page here →.

This page in Markdown → https://md.research.elamur.ai/free/en/authors/sina-zarriess/