Mapping distributional to model-theoretic semantic spaces: a baseline
This work addresses a specific issue in natural language processing for researchers, but it is incremental as it builds on existing methods with a baseline improvement.
The paper tackles the problem of mapping distributional semantic spaces to model-theoretic ones, showing that a simple baseline achieves a +51% relative improvement on one dataset and competitive results on another compared to a prior approach.
Word embeddings have been shown to be useful across state-of-the-art systems in many natural language processing tasks, ranging from question answering systems to dependency parsing. (Herbelot and Vecchi, 2015) explored word embeddings and their utility for modeling language semantics. In particular, they presented an approach to automatically map a standard distributional semantic space onto a set-theoretic model using partial least squares regression. We show in this paper that a simple baseline achieves a +51% relative improvement compared to their model on one of the two datasets they used, and yields competitive results on the second dataset.