Using Sentence Plausibility to Learn the Semantics of Transitive Verbs
This work addresses the challenge of semantic representation for transitive verbs in natural language processing, but it appears incremental as it builds on existing functional approaches.
The paper tackled the problem of representing transitive verbs in compositional distributional semantics by using a logistic regression classifier trained on a plausibility task to create verb matrices, finding that this approach may be more effective for disambiguation tasks compared to a common corpus-based method.
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 the plausibility training may be more effective for disambiguation tasks.