papers

Publications (5)

cs.CL2017

Improving Semantic Composition with Offset Inference

Thomas Kober, Julie Weeds, Jeremy Reffin +1

Count-based distributional semantic models suffer from sparsity due to unobserved but plausible co-occurrences in any text collection. This problem is amplified for models like Anc…

cs.AI2020

Causal datasheet: An approximate guide to practically assess Bayesian networks in the real world

Bradley Butcher, Vincent S. Huang, Jeremy Reffin +3

In solving real-world problems like changing healthcare-seeking behaviors, designing interventions to improve downstream outcomes requires an understanding of the causal links with…

cs.CL2017

One Representation per Word - Does it make Sense for Composition?

Thomas Kober, Julie Weeds, John Wilkie +2

In this paper, we investigate whether an a priori disambiguation of word senses is strictly necessary or whether the meaning of a word in context can be disambiguated through compo…

cs.CL2016

Aligning Packed Dependency Trees: a theory of composition for distributional semantics

David Weir, Julie Weeds, Jeremy Reffin +1

We present a new framework for compositional distributional semantics in which the distributional contexts of lexemes are expressed in terms of anchored packed dependency trees. We…

cs.CL2016

Improving Sparse Word Representations with Distributional Inference for Semantic Composition

Thomas Kober, Julie Weeds, Jeremy Reffin +1

Distributional models are derived from co-occurrences in a corpus, where only a small proportion of all possible plausible co-occurrences will be observed. This results in a very s…