Edinburgh Research Explorer A systematic comparison of methods for low-resource dependency parsing on genuinely low-resource languages

By Clara Vania, Yova Kementchedjhieva, Anders Søgaard, Adam Lopez

Subfields: Information Extraction, Computational Linguistics & Semantics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Extraction

1. Kevin Gimpel
2. Jannik Strotgen
3. Karen Livescu
4. Greg Durrett
5. Daniel Klein

In Computational Linguistics & Semantics

1. Kevin Gimpel
2. Karen Livescu

Citations in the corpus

• Substructure Substitution: Structured Data Augmentation for NLP (2021, background): “¸Sahin and Steedman (2018) show that subtree cropping and rotation based on dependency parse trees can help part-of-speech tagging for low-resource languages, while Vania et al. (2019) has demonstrated that such methods also help dependency parsing when very limited training data is available.”
• A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios (2020, methodology): “Operations that (depending on the task) do not change the label include manipulation of parts of the dependency tree (Şahin and Steedman, 2018; Vania et al., 2019; Dehouck and Gómez-Rodríguez, 2020), sim-”