SZTAKI HLT | Sentence Length

Sentence Length

Gábor Borbély, András Kornai

In Proceedings of the 16th Meeting on the Mathematics of Language, 2019

ACLWEB
Slides (PDF)

The distribution of sentence length in ordinary language is not well captured by the existing models. Here we survey previous models of sentence length and present our random walk model that offers both a better fit with the data and a better understanding of the distribution. We develop a generalization of KL divergence, discuss measuring the noise inherent in a corpus, and present a hyperparameter-free Bayesian model comparison method that has strong conceptual ties to Minimal Description Length modeling. The models we obtain require only a few dozen bits, orders of magnitude less than the naive nonparametric MDL models would.

Citation


        @inproceedings{borbely-kornai-2019-sentence,
    title = "Sentence Length",
    author = "Borb{\'e}ly, G{\'a}bor  and
      Kornai, Andr{\'a}s",
    booktitle = "Proceedings of the 16th Meeting on the Mathematics of Language",
    month = "18{--}19 " # jul,
    year = "2019",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/W19-5710",
    pages = "114--125",
}