Sina Zarrieß

3 paper cards in Mova's library · 2011–2023

Sina Zarrieß wrote 3 of the papers Mova reads, in 2011–2023, most of them on Machine translation; often with Aoife Cahill, David Schlangen, Jonas Kuhn.

The profile is the library's match of the name; two people with one name are not always told apart.

Papers

When Your Language Model Cannot Even Do Determiners Right: Probing for Anti-Presuppositions and the Maximize Presupposition! Principle (2023)
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.
Know What You Don't Know: Modeling a Pragmatic Speaker that Refers to Objects of Unknown Categories (2019)
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.
Underspecifying and Predicting Voice for Surface Realisation Ranking (2011)
The authors regenerate German corpus sentences with a reversible LFG grammar and a ranker that chooses among the candidate realisations.