Exploring Unsupervised Methods to Textual Similarity

This paper presents some unsupervised methods for detecting semantic textual similarity, which are based on distributional models and dependency parsing. The systems are evaluated using the dataset realased by the ASSIN Shared Task co-located with PROPOR 2016. The results do not improve the state-of-the-art for Portuguese language.

keywords: semantic textual similarity, dependency parsing, open information extaction