Mova0.5 pre-release⌕
☰
home / docs / papers / authors / Johan Bos

Johan Bos

9 paper cards in Mova's library · 1994–2021

Johan Bos wrote 9 of the papers Mova reads, in 1994–2021, most of them on Machine translation, Discourse analysis, Word sense disambiguation; often with Lasha Abzianidze, Rik van Noord, Chunliu Wang.

OpenAlex · ORCID · h-index 36 · 4636 citations · 187 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 7 · Discourse analysis 4 · Word sense disambiguation 1

Papers

  1. Evaluating Text Generation from Discourse Representation Structures (2021)
    The paper generates English from DRSs with a standard bi-LSTM sequence-to-sequence model, using a linearised DRS input and comparing a character-level decoder with a word-level one.
  2. DRS at MRP 2020: Dressing up Discourse Representation Structures as Graphs (2020)
    DRSs are nested boxes, but the 2020 shared task needed directed labelled graphs, so the authors describe how a DRS can be turned into a graph.
  3. The Parallel Meaning Bank: A Framework for Semantically Annotating Multiple Languages (2020)
    The paper describes the framework behind the PMB. English text gets seven annotation layers (segmentation, symbolisation, semantic tagging, word sense disambiguation, syntax, thematic roles and coreference), and the result is projected to translations. Projection breaks where word order, multiword expressions…
  4. The First Shared Task on Discourse Representation Structure Parsing (2019)
    The shared task asked participants to parse short English texts into Discourse Representation Structures (DRSs), given in clausal form.
  5. The Parallel Meaning Bank: Towards a Multilingual Corpus of Translations Annotated with Compositional Meaning Representations (2017)
    The Parallel Meaning Bank (PMB) annotates English texts with compositional meaning representations based on Discourse Representation Theory, and projects the annotation to translations through word alignment.
  6. Squib: Expressive Power of Abstract Meaning Representations (2016)
    The squib gives AMR a model-theoretic meaning by translating it into first-order logic. Basic AMRs, with concepts as predicates, roles as binary relations and role inversion, map to conjunctions of atomic formulas, and recurrent variables are handled as reuse of the same entity. Negation is added as a polarity flag…
  7. Towards Generating Text from Discourse Representation Structures (2011)
    The paper argues that Discourse Representation Structures are a good language-neutral input for generation, since they hold the content that a macro planner would produce (rhetorical structure, presupposition, named entities, thematic roles and word senses).
  8. Recognising Textual Entailment with Logical Inference (2005)
    The paper compares two domain-independent methods for recognising textual entailment on the RTE challenge data (567 development and 800 test pairs).
  9. Presupposition & VP-Ellipsis (1994)
    VP-ellipsis ("John kicked his dog, and Tom did, too") has a strict reading (Tom kicked John's dog) and a sloppy one (Tom kicked Tom's dog).

Co-authors (12)

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