Universal Dependencies: Principles and Tools (tutorial)

By Daniel Zeman. 2021

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. Hojin Kang
2. Tahmid Hasan
3. Yuan Cao
4. Yulia Tsvetkov
5. Melvin Johnson
6. Junjie Hu
7. Anders Søgaard
8. Graham Neubig

In Computational Linguistics & Semantics

1. Yoav Goldberg
2. Tahmid Hasan
3. Yuan Cao
4. Yulia Tsvetkov
5. Melvin Johnson
6. Junjie Hu
7. Anders Søgaard
8. Graham Neubig

Citations in the corpus

• XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization (2020, positive): “5 (Nivre et al., 2018) treebanks, which cover 90 languages.”
• TaTa: A Multilingual Table-to-Text Dataset for African Languages (2022, background): “…available in African languages mainly focus on classic NLP applications such as machine translation (Nekoto et al., 2020), dependency parsing (De Marneffe et al., 2021), named 4 An exception is the English–German RotoWire subset created for a shared task (Hayashi et al., 2019). entity…”
• BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Bangla (2021, methodology): “In future, we will include other Bangla NLU benchmarks (e.g., dependency parsing (de Marneffe et al., 2021)) in BLUB and investigate the benefits of initializing Bangla NLG models from BanglaBERT.”
• Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Loss (2016, background): “2 (Nivre et al., 2015) (17 POS) with the canonical data splits.”
• An Information Theoretic View on Selecting Linguistic Probes (2020, methodology): “Data We use the Universal Dependency (Zeman et al., 2019) dataset loaded with the Flair toolkit (Akbik et al., 2018).”
• Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models (2020, methodology): “In particular, the dataset we used is from the Universal Dependencies treebanks (Nivre et al., 2018).”
• Spanish Pre-trained BERT Model and Evaluation Data (2023, background): “4) Treebank (Nivre et al., 2016).”
• VECO: Variable Encoder-decoder Pre-training for Cross-lingual Understanding and Generation (2020, unknown): “, 2019); (2) structured prediction: UDPOS (Nivre et al., 2018), Wikiann NER (Pan et al.”