Corpus ID: 6054545

Paraphrase-Supervised Models of Compositionality

  title={Paraphrase-Supervised Models of Compositionality},
  author={Avneesh Singh Saluja and Chris Dyer and Jean-David Ruvini},
  • Avneesh Singh Saluja, Chris Dyer, Jean-David Ruvini
  • Published 2018
  • Computer Science
  • ArXiv
  • Compositional vector space models of meaning promise new solutions to stubborn language understanding problems. This paper makes two contributions toward this end: (i) it uses automatically-extracted paraphrase examples as a source of supervision for training compositional models, replacing previous work which relied on manual annotations used for the same purpose, and (ii) develops a context-aware model for scoring phrasal compositionality. Experimental results indicate that these multiple… CONTINUE READING

    Figures, Tables, and Topics from this paper.


    Publications referenced by this paper.
    An Empirical Study on Compositionality in Compound Nouns
    • 115
    • Highly Influential
    • PDF
    Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
    • 3,817
    • PDF
    Paraphrasing with Bilingual Parallel Corpora
    • 559
    • PDF
    Learning Translation Boundaries for Phrase-Based Decoding
    • 40
    • PDF
    Estimating Linear Models for Compositional Distributional Semantics
    • 130
    • PDF
    Computing Semantic Compositionality in Distributional Semantics
    • 47
    • PDF
    A practical and linguistically-motivated approach to compositional distributional semantics
    • 61
    • PDF