Improved Information Structure Analysis of Scientific Documents Through Discourse and Lexical Constraints
Yufan Guo, Roi Reichart, Anna Korhonen · 2013
Inferring the information structure of scientific documents is useful for many downstream applications. Existing feature-based machine learning approaches to this task require substantial training data and suffer from limited performance. Our idea is to guide feature-based models with declarative domain knowledge encoded as posterior distribution constraints. We explore a rich set of discourse and lexical constraints which we incorporate through the Generalized Expectation (GE) criterion. Our constrained model improves the performance of existing fully and lightly supervised models. Even a fully unsupervised version of this model outperforms lightly supervised feature-based models, showing that our approach can be useful even when no labeled data is available. 1