Aggregated Word Pair Features for Implicit Discourse Relation Disambiguation

Biran, Or; McKeown, Kathleen

We present a reformulation of the word pair features typically used for the task of disambiguating implicit relations in the Penn Discourse Treebank. Our word pair features achieve significantly higher performance than the previous formulation when evaluated without additional features. In addition, we present results for a full system using additional features which achieves close to state of the art performance without resorting to gold syntactic parses or to context outside the relation.


Also Published In

Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics
The Association for Computational Linguistics

More About This Work

Academic Units
Computer Science
Published Here
October 4, 2013