Mova0.5 pre-release⌕
☰
home / docs / papers / authors / Bernd Bohnet

Bernd Bohnet

7 paper cards in Mova's library · 2010–2020

Bernd Bohnet wrote 7 of the papers Mova reads, in 2010–2020, most of them on Machine translation, Dependency parsing, Treebanks; often with Leo Wanner, Simon Mille, Alicia Burga.

OpenAlex · h-index 27 · 4405 citations · 103 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 5 · Dependency parsing 2 · Treebanks 1

Papers

  1. The Third Multilingual Surface Realisation Shared Task (SR'20): Overview and Evaluation Results (2020)
    The third edition of the surface realisation task keeps the two tracks of the earlier editions: a shallow track with unordered lemmatised UD trees, and a deep track that also removes function words and morphology.
  2. Recursive LSTM Tree Representation for Arc-Standard Transition-Based Dependency Parsing (2019)
    The paper encodes a partial dependency tree as one dense vector, built by applying LSTMs recursively to each head and its dependents.
  3. The First Multilingual Surface Realisation Shared Task (SR'18): Overview and Evaluation Results (2018)
    The report presents the first multilingual shared task on surface realisation, the step that turns an unordered dependency tree into a sentence.
  4. Underspecified Universal Dependency Structures as Inputs for Multilingual Surface Realisation (2018)
    The paper describes how the input data of the SR'18 task were derived from UD v2.0 treebanks. The shallow inputs are made by removing word order and lemmatising tokens, which is a set of replacement rules. The deep inputs are harder to make. Auxiliaries, functional prepositions and conjunctions are removed, and…
  5. Towards the Annotation of Penn TreeBank with Information Structure (2013)
    Information structure (here the thematicity part of Meaning-Text Theory's communicative structure: Specifier, Theme, Rheme, nested) is missing from the big English treebanks.
  6. Generating Non-Projective Word Order in Statistical Linearization (2012)
    A projective linearizer can only produce word orders in which no two edges cross, and many languages need crossings.
  7. Broad Coverage Multilingual Deep Sentence Generation with a Stochastic Multi-Level Realizer (2010)
    The paper describes a multilingual generator that starts from deep, predicate-argument-like structures and produces sentences in several languages.

Co-authors (13)

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