Clustering Clauses for High-Level Relation Detection: An Information-theoretic Approach

Recently, there has been a rise of interest in unsupervised detection of highlevel semantic relations involving complex units, such as phrases and whole sentences. Typically such approaches are faced with two main obstacles: data sparseness and correctly generalizing from the examples. In this work, we describe the Clustered Clause representation, which utilizes information-based clustering and inter-sentence dependencies to create a simplified and generalized representation of the grammatical clause. We implement an algorithm which uses this representation to detect a predefined set of high-level relations, and demonstrate our model’s effectiveness in overcoming both the problems mentioned.