A Little Pretraining Goes a Long Way: A Case Study on Dependency Parsing Task for Low-resource Morphologically Rich Languages

Neural dependency parsing has achieved remarkable performance for many\ndomains and languages. The bottleneck of massive labeled data limits the\neffectiveness of these approaches for low resource languages. In this work, we\nfocus on dependency parsing for morphological rich languages (MRLs) in a\nlow-resource setting. Although morphological information is essential for the\ndependency parsing task, the morphological disambiguation and lack of powerful\nanalyzers pose challenges to get this information for MRLs. To address these\nchallenges, we propose simple auxiliary tasks for pretraining. We perform\nexperiments on 10 MRLs in low-resource settings to measure the efficacy of our\nproposed pretraining method and observe an average absolute gain of 2 points\n(UAS) and 3.6 points (LAS). Code and data available at:\nhttps://github.com/jivnesh/LCM\n