Domain Agnostic Real-Valued Specificity Prediction


  • Wei-Jen Ko University of Texas at Austin
  • Greg Durrett University of Texas at Austin
  • Junyi Jessy Li University of Texas at Austin



Sentence specificity quantifies the level of detail in a sentence, characterizing the organization of information in discourse. While this information is useful for many downstream applications, specificity prediction systems predict very coarse labels (binary or ternary) and are trained on and tailored toward specific domains (e.g., news). The goal of this work is to generalize specificity prediction to domains where no labeled data is available and output more nuanced realvalued specificity ratings.We present an unsupervised domain adaptation system for sentence specificity prediction, specifically designed to output real-valued estimates from binary training labels. To calibrate the values of these predictions appropriately, we regularize the posterior distribution of the labels towards a reference distribution. We show that our framework generalizes well to three different domains with 50%-68% mean absolute error reduction than the current state-of-the-art system trained for news sentence specificity. We also demonstrate the potential of our work in improving the quality and informativeness of dialogue generation systems.




How to Cite

Ko, W.-J., Durrett, G., & Li, J. J. (2019). Domain Agnostic Real-Valued Specificity Prediction. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 6610-6617.



AAAI Technical Track: Natural Language Processing