Learning Semantically and Additively Compositional Distributional Representations
This work addresses the challenge of integrating distributional semantics with logical structures for natural language processing, offering incremental improvements in tasks like phrase similarity and sentence completion.
The paper tackles the problem of connecting vector-based composition models to formal semantics, specifically Dependency-based Compositional Semantics (DCS), and shows that this approach achieves near state-of-the-art performance on phrase similarity tasks and sets a new state-of-the-art on sentence completion.
This paper connects a vector-based composition model to a formal semantics, the Dependency-based Compositional Semantics (DCS). We show theoretical evidence that the vector compositions in our model conform to the logic of DCS. Experimentally, we show that vector-based composition brings a strong ability to calculate similar phrases as similar vectors, achieving near state-of-the-art on a wide range of phrase similarity tasks and relation classification; meanwhile, DCS can guide building vectors for structured queries that can be directly executed. We evaluate this utility on sentence completion task and report a new state-of-the-art.