Aggregated Word Pair Features for Implicit Discourse Relation Disambiguation
Columbia Academic Commons (Columbia University)2013pp. 69–73
Citations Over TimeTop 1% of 2013 papers
Abstract
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.
Related Papers
- The Penn Discourse TreeBank 2.0.(2008)
- → Automatic sense prediction for implicit discourse relations in text(2009)287 cited
- → Recognizing implicit discourse relations in the Penn Discourse Treebank(2009)282 cited
- → Discovering Implicit Discourse Relations Through Brown Cluster Pair Representation and Coreference Patterns(2014)131 cited
- → Improving Implicit Discourse Relation Recognition Through Feature Set Optimization(2012)117 cited