Detecting dangerous coordination ambiguities using word distribution
Francis Chantree, Alistair Willis, Adam Kilgarriff, Anne N. De Roeck · Amsterdam studies in the theory and history of linguistic science. Series 4, Current issues in linguistic theory · 2007
In this paper we present heuristics for resolving coordination ambiguities. We test the hypothesis that the most likely reading of a coordination can be predicted using word distribution information from a generic corpus. Our heuristics are based upon the relative frequency of the coordination in the corpus, the distributional similarity of the coordinated words, and the collocation frequency between the coordinated words and their modifiers. These heuristics have varying but useful predictive power. They also take into account our view that many ambiguities cannot be effectively disambiguated, since human perceptions vary widely.