Anders Søgaard · page 2

29 papers in our library · 2011–2026 · page 2 of 2

Papers

The most cited first (OpenAlex and our library).

Model-based Annotation of Coreference (2020 · 8 citations)
Standard coreference annotation asks people to connect pronouns with earlier text spans. The authors argue this is unnatural, because readers reason over a mental model of the entities a text describes rather than over strings. They propose model-based annotation instead. Documents are first linked to a knowledge…
An Empirical Study of Differences between Conversion Schemes and Annotation Guidelines (2013 · 3 citations)
Many dependency treebanks are converted from constituency treebanks, and different conversion schemes make different choices about heads and relation labels.
Few-Shot and Zero-Shot Learning for Historical Text Normalization (2019 · 2 citations)
The paper evaluates 63 multi-task configurations of an encoder-decoder normaliser on ten datasets in eight languages.
LLM Beliefs Are in Their Heads (2026)
The paper asks whether decoder-only LLMs have internal states that could count as beliefs. It tests them against four standards from Herrmann and Levinstein (2025): Accuracy, Use, Coherence and Uniformity. The authors study six model families: GPT-2, Llama-3.1-8B, Gemma-2-9B, Yi-6B, Pythia-6.9B and GPT-J-6B, using…