---
title: "Stefan Grünewald — papers and cards"
description: "Stefan Grünewald: 3 paper cards in the Research library (2020–2021), with what each paper is about, the ideas Mova took from it, and the co-authors."
canonical: "https://research.elamur.ai/free/en/authors/stefan-grunewald/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/stefan-grunewald/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Stefan Grünewald

# Stefan Grünewald

3 paper cards in the Research library · 2020–2021

Stefan Grünewald wrote 3 of the papers Mova reads, in 2020–2021, most of them on [Universal Dependencies](https://md.research.elamur.ai/free/en/topics/universal-dependencies/), [Dependency parsing](https://md.research.elamur.ai/free/en/topics/dependency-parsing/); often with [Annemarie Friedrich](https://md.research.elamur.ai/free/en/authors/annemarie-friedrich/), [Jonas Kuhn](https://md.research.elamur.ai/free/en/authors/jonas-kuhn/), Prisca Piccirilli.

Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Stefan+Gr%C3%BCnewald) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Stefan+Gr%C3%BCnewald) · [dblp](https://dblp.org/search?q=Stefan+Gr%C3%BCnewald) · [ACL Anthology](https://aclanthology.org/search/?q=Stefan+Gr%C3%BCnewald) · [ORCID](https://orcid.org/orcid-search/search?searchQuery=Stefan+Gr%C3%BCnewald)

Topics: [Universal Dependencies](https://md.research.elamur.ai/free/en/topics/universal-dependencies/) 3 · [Dependency parsing](https://md.research.elamur.ai/free/en/topics/dependency-parsing/) 1

## Papers

1. **[Applying Occam's Razor to Transformer-Based Dependency Parsing: What Works, What Doesn't, and What is Really Necessary](https://md.research.elamur.ai/free/en/papers/grunewald-2021-applying-occam-s-razor-transformer/)** *(2021)* `measured` Modern graph-based dependency parsers for Universal Dependencies rely on transformer embeddings but differ in several design choices: which pretrained model to use, whether to add LSTM layers, and whether to train jointly on POS and morphology.
2. **[Coordinate Constructions in English Enhanced Universal Dependencies: Analysis and Computational Modeling](https://md.research.elamur.ai/free/en/papers/grunewald-2021-coordinate-constructions-english-enhanced-universal/)** *(2021)* In Enhanced UD, coordination is represented by propagating the first conjunct's relations (its head and its dependents) to the other conjuncts.
3. **[RobertNLP at the IWPT 2020 Shared Task: Surprisingly Simple Enhanced UD Parsing for English](https://md.research.elamur.ai/free/en/papers/ud-2020-grunewald-robertnlp-iwpt-2020-shared-task/)** *(2020)* RobertNLP builds enhanced UD graphs directly, without a basic tree first. A biaffine classifier over fine-tuned RoBERTa embeddings scores every ordered pair of tokens with a label or with "no relation". Labels that carry words (such as obl:instead_of) are replaced by placeholders, for example obl:[case], which cuts…

## Co-authors (3)

- [Annemarie Friedrich](https://md.research.elamur.ai/free/en/authors/annemarie-friedrich/) ×3
- [Jonas Kuhn](https://md.research.elamur.ai/free/en/authors/jonas-kuhn/)
- Prisca Piccirilli