The 2nd Workshop on Continuous Vector Space Models and their Compositionality (CVSC) will be hosted by the 14th Conference of the European Chapter of the Association for Computational Linguistics (EACL), on April 27th 2014, in Gothenburg, Sweden.
The first workshop on Continuous Vector Space Models and their Compositionality attempted to bridge the communities working on various kinds of semantics models relying on continuous representations of textual data.
This year, we continue in this direction and also expend our call for papers to work that asks theoretical and conceptual questions too, such as: Should phrase representations and word representations be of the same sort? Could different linguistic levels require different modelling approaches? Is compositionality determined by syntax, and if so, how do we learn/define it? Should word representations be fixed and obtained distributionally, or should the encoding be variable? Should word representations be task-specific, or should they be general?
Hence, this year's list of topics is as following:
In brief, we aim to continue the ongoing effort to address some of these points, either by theoretical reasoning, or through example via demonstrating interesting properties of new or existing distributional models of semantics. We hope to gather formal semanticists, computational linguists, machine learning researchers and computational neuroscientists to tackle these fascinating problems.