@article{TACL472,
        author = {Yufan Guo and Roi Reichart and Anna Korhonen},
        title = {Unsupervised Declarative Knowledge Induction for Constraint-Based
Learning of Information Structure in Scientific Documents},
        journal = {Transactions of the Association for Computational Linguistics},
        volume = {3},
        year = {2015},
        keywords = {},
        abstract = {Inferring the information structure of scientific documents is
useful for many NLP applications. Existing approaches to this task require
substantial human effort. We propose a framework for constraint learning
that reduces human involvement considerably. Our model uses topic models to
identify latent topics and their key linguistic features in input documents,
induces constraints from this information and maps sentences to their
dominant information structure categories through a constrained unsupervised
model. When the induced constraints are combined with a fully unsupervised
model, the resulting model challenges existing lightly supervised
feature-based models as well as unsupervised models that use manually
constructed declarative knowledge. Our results demonstrate that useful
declarative knowledge can be learned from data with very limited human
involvement.},
        issn = {2307-387X},
        url =
{https://tacl2013.cs.columbia.edu/ojs/index.php/tacl/article/view/472},
        pages = {131--143}
}