A Factorized Model for Transitive Verbs in Compositional Distributional Semantics
This work addresses a specific linguistic modeling problem in computational semantics, representing an incremental improvement over existing methods.
The authors tackled the problem of representing transitive verb constructions in compositional distributional semantics by developing a factorized model that separately models subject-verb and verb-object relationships before combining them. Their model outperformed recent previous work on two established tasks for transitive verb constructions.
We present a factorized compositional distributional semantics model for the representation of transitive verb constructions. Our model first produces (subject, verb) and (verb, object) vector representations based on the similarity of the nouns in the construction to each of the nouns in the vocabulary and the tendency of these nouns to take the subject and object roles of the verb. These vectors are then combined into a final (subject,verb,object) representation through simple vector operations. On two established tasks for the transitive verb construction our model outperforms recent previous work.