jivnesh / lcm Goto Github PK

conda install pytorch==1.1.0 torchvision==0.3.0 cudatoolkit=9.0 -c pytorch
pip install gensim==3.8.1

@inproceedings{sandhan-etal-2021-little,
    title = "A Little Pretraining Goes a Long Way: A Case Study on Dependency Parsing Task for Low-resource Morphologically Rich Languages",
    author = "Sandhan, Jivnesh  and Krishna, Amrith  and Gupta, Ashim  and Behera, Laxmidhar  and Goyal, Pawan",
    booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop",
    month = apr,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.eacl-srw.16",
    doi = "10.18653/v1/2021.eacl-srw.16",
    pages = "111--120",
    abstract = "Neural dependency parsing has achieved remarkable performance for many domains and languages. The bottleneck of massive labelled data limits the effectiveness of these approaches for low resource languages. In this work, we focus on dependency parsing for morphological rich languages (MRLs) in a low-resource setting. Although morphological information is essential for the dependency parsing task, the morphological disambiguation and lack of powerful analyzers pose challenges to get this information for MRLs. To address these challenges, we propose simple auxiliary tasks for pretraining. We perform experiments on 10 MRLs in low-resource settings to measure the efficacy of our proposed pretraining method and observe an average absolute gain of 2 points (UAS) and 3.6 points (LAS).",
}