CSSL: Contrastive Self-Supervised Learning for Dependency Parsing on Relatively Free Word Ordered and Morphologically Rich Low Resource Languages
Abstract: Significant advancements have been made in the domain of dependency parsing, with researchers introducing novel architectures to enhance parsing performance. However, the majority of these architectures have been evaluated predominantly in languages with a fixed word order, such as English. Consequently, little attention has been devoted to exploring the robustness of these architectures in the context of relatively free word-ordered languages. In this work, we examine the robustness of graph-based parsing architectures on 7 relatively free word order languages. We focus on investigating essential modifications such as data augmentation and the removal of position encoding required to adapt these architectures accordingly.
To this end, we propose a contrastive self-supervised learning method to make the model robust to word order variations. Furthermore, our proposed modification demonstrates a substantial average gain of 3.03/2.95 points in 7 relatively free word order languages, as measured by the Unlabelled/Labelled Attachment Score metric when compared to the best performing baseline.
Paper Type: Short
Research Area: Syntax: Tagging, Chunking and Parsing
Research Area Keywords: dependency parsing, morphologically-rich languages, contrastive learning, low resource languages
Contribution Types: NLP engineering experiment, Approaches to low-resource settings
Languages Studied: Sanskrit, Turkish, Telugu, Gothic, Hungarian, Ancient Hebrew, Lithuanian
Submission Number: 702
Loading