Date of this Version
We report results on predicting the sense of implicit discourse relations between adjacent sentences in text. Our investigation concentrates on the association between discourse relations and properties of the referring expressions that appear in the related sentences. The properties of interest include coreference information, grammatical role, information status and syntactic form of referring expressions. Predicting the sense of implicit discourse relations based on these features is considerably better than a random baseline and several of the most discriminative features conform with linguistic intuitions. However, these features do not perform as well as lexical features traditionally used for sense prediction.
Louis, Annie; Joshi, Aravind K.; Prasad, Rashmi; and Nenkova, Ani, "Using Entity Features to Classify Implicit Discourse Relations" (2010). Departmental Papers (CIS). Paper 712.
Date Posted: 30 July 2012