Abstract: Semantic relations are often signaled with prepositional or possessive marking—but extreme polysemy bedevils their analysis and automatic interpretation. We introduce a new annotation scheme, corpus, and task for the disambigua-tion of prepositions and possessives in English. Unlike previous approaches, our annotations are comprehensive with respect to types and tokens of these markers; use broadly applicable supersense classes rather than ﬁne-grained dictionary deﬁnitions; unite prepositions and possessives under the same class inventory; and distinguish between a marker’s lexical contribution and the role it marks in the context of a predicate or scene. Strong interannotator agreement rates, as well as encouraging disambiguation results with established supervised methods, speak to the viability of the scheme and task.
Authors: Nathan Schneider, Jena D. Hwang, Vivek Srikumar, Jakob Prange, Austin Blodgett, Sarah R. Moeller, Aviram Stern, Adi Bitan, Omri Abend (Georgetown University, IHMC, University of Utah, University of Colorado Boulder, Hebrew University of Jerusalem)