Stefan Grünewald
Stefan Grünewald wrote 3 of the papers Mova reads, in 2020–2021, most of them on Universal Dependencies, Dependency parsing; often with Annemarie Friedrich, Jonas Kuhn, Prisca Piccirilli.
Topics: Universal Dependencies 3 · Dependency parsing 1
Papers
- Applying Occam's Razor to Transformer-Based Dependency Parsing: What Works, What Doesn't, and What is Really Necessary (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. - Coordinate Constructions in English Enhanced Universal Dependencies: Analysis and Computational Modeling (2021)
In Enhanced UD, coordination is represented by propagating the first conjunct's relations (its head and its dependents) to the other conjuncts. - RobertNLP at the IWPT 2020 Shared Task: Surprisingly Simple Enhanced UD Parsing for English (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 ×3
- Jonas Kuhn
- Prisca Piccirilli
This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/authors/stefan-grunewald/