Mova0.5 pre-release⌕
☰
home / docs / papers / authors / Marcel Bollmann

Marcel Bollmann

9 paper cards in Mova's library · 2011–2019

Marcel Bollmann wrote 9 of the papers Mova reads, in 2011–2019, most of them on Machine translation, Part-of-speech tagging; often with Anders Søgaard, Florian Petran, Joachim Bingel.

OpenAlex · ORCID · h-index 11 · 337 citations · 42 works — openalex, 2026-10-18

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

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology · ORCID

Topics: Machine translation 2 · Part-of-speech tagging 1

Papers

  1. A Large-Scale Comparison of Historical Text Normalization Systems (2019)
    The paper compares historical spelling normalization systems across eight languages, covering rule-based, distance-based, character statistical MT and neural approaches.
  2. Historical Text Normalization with Delayed Rewards (2019)
    Sequence-to-sequence normalisers are usually trained with token-level maximum likelihood. The paper fine-tunes such a model with policy gradient, so that the training signal is the exact match of the whole normalisation, a delayed reward. Six historical datasets are used. Fine-tuning reduces the error by 20% for…
  3. Few-Shot and Zero-Shot Learning for Historical Text Normalization (2019)
    The paper evaluates 63 multi-task configurations of an encoder-decoder normaliser on ten datasets in eight languages.
  4. Multi-task learning for historical text normalization: Size matters (2018)
    The paper asks when multi-task learning helps historical normalisation. It tests an encoder-decoder model with and without auxiliary tasks on 10 datasets from 8 languages, from German and English to Hungarian, Icelandic, Slovene, Spanish, Portuguese and Swedish. Most datasets either always gain or always lose from…
  5. Learning attention for historical text normalization by learning to pronounce (2017)
    The paper treats historical normalisation as a character-level transduction with an encoder-decoder RNN, so no explicit character alignment is needed.
  6. Improving historical spelling normalization with bi-directional LSTMs and multi-task learning (2016)
    The paper frames historical spelling normalisation as character-level sequence labelling and uses a bi-directional LSTM for it.
  7. Evaluating Inter-Annotator Agreement on Historical Spelling Normalization (2016)
    Normalisation labels are open and sparse, and most tokens are close to their surface form, so the usual agreement measures do not fit the task well.
  8. POS Tagging for Historical Texts with Sparse Training Data (2013)
    The paper tags historical German (1400–1770) in two steps. First, the Norma tool normalises the spelling to modern forms. Second, a tagger trained on modern German tags the normalised text. The normaliser needs only a few hundred hand-normalised tokens per text. Before normalisation, the text matches the gold…
  9. Rule-Based Normalization of Historical Texts (2011)
    The paper normalizes Early New High German spelling to modern forms using only unsupervised learning and freely available resources.

Co-authors (6)

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/authors/marcel-bollmann/