Corpus ID: 4644664

Using Sentence Plausibility to Learn the Semantics of Transitive Verbs

  title={Using Sentence Plausibility to Learn the Semantics of Transitive Verbs},
  author={T. Polajnar and Laura Rimell and S. Clark},
The functional approach to compositional distributional semantics considers transitive verbs to be linear maps that transform the distributional vectors representing nouns into a vector representing a sentence. We conduct an initial investigation that uses a matrix consisting of the parameters of a logistic regression classifier trained on a plausibility task as a transitive verb function. We compare our method to a commonly used corpus-based method for constructing a verb matrix and find that… Expand
8 Citations
Learning Embeddings for Transitive Verb Disambiguation by Implicit Tensor Factorization
  • 11
  • Highly Influenced
  • PDF
An Exploration of Discourse-Based Sentence Spaces for Compositional Distributional Semantics
  • 26
  • PDF
Exploring Semantic Incrementality with Dynamic Syntax and Vector Space Semantics
  • 5
  • PDF
Evaluating Composition Models for Verb Phrase Elliptical Sentence Embeddings
  • 10
  • PDF
Permutation Invariant Gaussian Matrix Models
  • 2
  • PDF


Experimental Support for a Categorical Compositional Distributional Model of Meaning
  • 316
  • Highly Influential
  • PDF
Experimenting with Transitive Verbs in a DisCoCat
  • 60
  • PDF
Prior Disambiguation of Word Tensors for Constructing Sentence Vectors
  • 69
  • PDF
Vector Space Semantic Parsing: A Framework for Compositional Vector Space Models
  • 32
  • PDF
Reducing Dimensions of Tensors in Type-Driven Distributional Semantics
  • 18
  • PDF
Vector-based Models of Semantic Composition
  • 689
  • PDF
Improving Distributional Semantic Vectors through Context Selection and Normalisation
  • 38
  • PDF
Mathematical Foundations for a Compositional Distributional Model of Meaning
  • 421
  • PDF