Mova0.5 pre-release⌕
☰
home / docs / papers / authors / Sebastian Schuster

Sebastian Schuster

12 paper cards in Mova's library · 2016–2024

Sebastian Schuster wrote 12 of the papers Mova reads, in 2016–2024, most of them on Universal Dependencies, Treebanks, Implicature; often with Christopher D. Manning, Joakim Nivre, Filip Ginter.

OpenAlex · ORCID · h-index 16 · 2576 citations · 93 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: Universal Dependencies 4 · Treebanks 3 · Implicature 1 · Coreference resolution 1

Papers

  1. SIGA: A Naturalistic NLI Dataset of English Scalar Implicatures with Gradable Adjectives (2024)
    SIGA is a set of naturally occurring scalar implicatures with gradable adjectives. The authors mine the C4 web corpus for the reinforcement frame «WEAK but not STRONG» («good but not great»), using 88 adjective scale pairs from de Melo & Bansal (2013). The frame guarantees which scale the writer had in mind. Deleting…
  2. Expectations over Unspoken Alternatives Predict Pragmatic Inferences (2023)
    Scalar inferences ("some" implies "not all") vary a lot from one instance to another, and across scales such as "good, excellent".
  3. Can language models capture syntactic associations without surface cues? A case study of reflexive anaphor licensing in English control constructions (2022)
    In "The lawyer promised the artist to make fun of himself", the reflexive himself must agree with the subject (the controller), while in "The lawyer persuaded the artist to make fun of himself" it must agree with the object.
  4. NOPE: A Corpus of Naturally-Occurring Presuppositions in English (2021)
    NOPE collects about 1,280 corpus passages, each with a presupposition trigger of one of ten types: change of state, aspectual verbs (begin, stop), clause-embedding verbs (know, realize, say), clefts, comparatives, embedded questions, implicatives (manage to, fail to), numeric determiners (both), re- verbs, and…
  5. Predicting scalar inferences from "or" to "not both" using neural sentence encoders (2021)
    A short paper extending the «some → not all» strength studies (Degen 2015; Schuster et al. 2020) to «or → not both». 1,244 Switchboard sentences with or were rated, in context, for how close they are to the same sentence with «but not both» added, on a slider and on a 1–7 scale. Strength varies widely and individual…
  6. Harnessing the linguistic signal to predict scalar inferences (2020)
    The paper asks whether a neural sentence encoder can predict how strongly listeners draw the «not all» inference from an utterance with some.
  7. Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection (2020)
    The paper describes the UD v2 guidelines and the state of the collection at release 2.5: 157 treebanks in 90 languages, built by more than 300 contributors.
  8. Enhancing Universal Dependency Treebanks: A Case Study (2018)
    Only five of the 102 UD 2.1 treebanks have enhanced dependencies, so the authors test whether enhanced graphs can be added to other treebanks automatically.
  9. Sentences with Gapping: Parsing and Reconstructing Elided Predicates (2018)
    In "Paul likes coffee and Mary tea" the verb is elided, so standard parsers attach the remnants badly and downstream relation extraction misses the predicate.
  10. CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies (2017)
    The shared task asks systems to parse raw text, with no gold tokenization, sentence splitting or tags, into UD trees for 49 languages.
  11. Gapping Constructions in Universal Dependencies v2 (2017)
    This is a design paper rather than an experiment. It asks how gapping (the omission of a repeated verb, as in "John likes tea, and Mary coffee") should be represented in UD v2. The authors survey the cross-linguistic patterns of gapping, including languages where the overt verb sits in the last conjunct, and compare…
  12. Enhanced English Universal Dependencies: An Improved Representation for Natural Language Understanding Tasks (2016)
    Shallow understanding tasks such as relation extraction need direct links between content words, which a strict basic tree lacks: in "Fred started to laugh" the controlled verb has no subject edge.

Co-authors (78)

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