Content Modeling Using Latent Permutations

Abstract

We present a novel Bayesian topic model for learning discourse-level document structure. Our model leverages insights from discourse theory to constrain latent topic assignments in a way that reflects the underlying organization of document topics. We propose a global model in which both topic selection and ordering are biased to be similar across a collection of related documents. We show that this space of orderings can be effectively represented using a distribution over permutations called the Generalized Mallows Model. We apply our method to three complementary discourse-level tasks: cross-document alignment, document segmentation, and information ordering. Our experiments show that incorporating our permutation-based model in these applications yields substantial improvements in performance over previously proposed methods.

References in corpus (3)

• Inferring Strategies for Sentence Ordering in Multidocument News Summarization
• Catching the Drift: Probabilistic Content Models, with Applications to Generation and Summarization
• Consensus ranking under the exponential model

Cited by in corpus (5)

• Generating Natural Language Descriptions from OWL Ontologies: the NaturalOWL System
• Boosting Entity Linking Performance by Leveraging Unlabeled Documents
• Optimal Learning of Mallows Block Model
• Jointly Modeling Topics and Intents with Global Order Structure
• Coarse-grained Cross-lingual Alignment of Comparable Texts with Topic Models and Encyclopedic Knowledge