Unsupervised discourse constituency parsing using viterbi em

13Citations
Citations of this article
77Readers
Mendeley users who have this article in their library.
Get full text

Abstract

In this paper, we introduce an unsupervised discourse constituency parsing algorithm. We use Viterbi EM with a margin-based criterion to train a span-based discourse parser in an unsupervised manner. We also propose initialization methods for Viterbi training of discourse constituents based on our prior knowledge of text structures. Experimental results demonstrate that our unsupervised parser achieves comparable or even superior performance to fully supervised parsers. We also investigate discourse constituents that are learned by our method.

Cite

CITATION STYLE

APA

Nishida, N., & Nakayama, H. (2020). Unsupervised discourse constituency parsing using viterbi em. Transactions of the Association for Computational Linguistics, 8, 215–230. https://doi.org/10.1162/tacl_a_00312

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free