Multilingual Unsupervised Dependency Parsing with Unsupervised POS tags

Abstract

In this paper, we present experiments with unsupervised dependency parser without using any part-of-speech tags learned from manually annotated data. We use only unsupervised word-classes and therefore propose fully unsupervised approach of sentence structure induction from a raw text.

We show that the results are not much worse than the results with supervised part-of-speech tags.

Keywords

• multilingual
• unsupervised
• dependency
• parsing
• with
• unsupervised
• tags