Harnessing the linguistic signal to predict scalar inferences

  title={Harnessing the linguistic signal to predict scalar inferences},
  author={Sebastian Schuster and Yuxing Chen and Judith Degen},
  • Sebastian Schuster, Yuxing Chen, Judith Degen
  • Published in ACL 2020
  • Computer Science
  • Pragmatic inferences often subtly depend on the presence or absence of linguistic features. For example, the presence of a partitive construction (of the) increases the strength of a so-called scalar inference: listeners perceive the inference that Chris did not eat all of the cookies to be stronger after hearing "Chris ate some of the cookies" than after hearing the same utterance without a partitive, "Chris ate some cookies." In this work, we explore to what extent neural network sentence… CONTINUE READING
    3 Citations

    Figures, Tables, and Topics from this paper

    Explore Further: Topics Discussed in This Paper


    Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies
    • 427
    • Highly Influential
    • PDF
    Colors in Context: A Pragmatic Neural Model for Grounded Language Understanding
    • 50
    • PDF
    Neural Network Acceptability Judgments
    • 225
    • PDF
    Scalar implicatures or focus: an experimental approach
    • 29
    Neural Language Models as Psycholinguistic Subjects: Representations of Syntactic State
    • 33
    • Highly Influential
    • PDF
    Speaker knowledge influences the comprehension of pragmatic inferences.
    • 69
    • PDF
    Investigating BERT's Knowledge of Language: Five Analysis Methods with NPIs
    • 37
    • PDF
    Reasoning about Pragmatics with Neural Listeners and Speakers
    • 84
    • PDF