Corpus ID: 227230348

QANom: Question-Answer driven SRL for Nominalizations

@inproceedings{Klein2020QANomQD,
  title={QANom: Question-Answer driven SRL for Nominalizations},
  author={Ayal Klein and Jonathan Mamou and Valentina Pyatkin and Daniela Stepanov and Hangfeng He and D. Roth and Luke Zettlemoyer and I. Dagan},
  booktitle={COLING},
  year={2020}
}
  • Ayal Klein, Jonathan Mamou, +5 authors I. Dagan
  • Published in COLING 2020
  • Computer Science
  • We propose a new semantic scheme for capturing predicate-argument relations for nominalizations, termed QANom. This scheme extends the QA-SRL formalism (He et al., 2015), modeling the relations between nominalizations and their arguments via natural language question-answer pairs. We construct the first QANom dataset using controlled crowdsourcing, analyze its quality and compare it to expertly annotated nominal-SRL annotations, as well as to other QA-driven annotations. In addition, we train a… CONTINUE READING

    Figures and Tables from this paper

    References

    SHOWING 1-10 OF 46 REFERENCES
    Large-Scale QA-SRL Parsing
    • 37
    • PDF
    Question-Answer Driven Semantic Role Labeling: Using Natural Language to Annotate Natural Language
    • 111
    • PDF
    QuASE: Question-Answer Driven Sentence Encoding
    • 6
    • PDF
    Unsupervised Transfer of Semantic Role Models from Verbal to Nominal Domain
    • 1
    • PDF
    Controlled Crowdsourcing for High-Quality QA-SRL Annotation
    • 6
    • PDF
    Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling
    • 114
    • PDF
    Improving Implicit Semantic Role Labeling by Predicting Semantic Frame Arguments
    • 13
    • PDF
    Semantic Role Labeling of Implicit Arguments for Nominal Predicates
    • 60
    • PDF
    Semantic Role Labeling of NomBank: A Maximum Entropy Approach
    • 55
    • PDF
    Broad-Coverage Semantic Dependency Parsing
    • 94