Universal Dependencies 2.1

By Joakim Nivre, Zeljko Agic, Lars Ahrenberg, Lene Antonsen, M. J. Aranzabe, Masayuki Asahara, Luma Ateyah, Mohammed Attia, Aitziber Atutxa, L. Augustinus and 204 more. 2017

425 citations recorded by the source corpus.

Subfields: Natural Language Processing, Evaluation & Benchmarks

How researchers see this paper

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

In Natural Language Processing

In Evaluation & Benchmarks

Citations in the corpus

Evaluating the Cross-Lingual Effectiveness of Massively Multilingual Neural Machine Translation (2019, background): “C L ] 1 S ep 2 01 9 shot cross-lingual POS tagging [Universal Dependencies 2.3 dataset (Nivre et al., 2018)], intent classification (Schuster et al., 2018), and achieve results comparable to state-of-the-art on document classification [ML-Doc dataset (Schwenk and Li, 2018)].”
A Monolingual Approach to Contextualized Word Embeddings for Mid-Resource Languages (2020, methodology): “Ortiz Suárez et al. (2019) reproduced the pipeline proposed by (Grave et al.”
X-FACTR: Multilingual Factual Knowledge Retrieval from Pretrained Language Models (2020, background): “, 2018; Artetxe and Schwenk, 2019), syntactic prediction (Nivre et al., 2018; Pan et al., 2017), and comprehensive benchmarks covering multiple tasks (Hu et al.”
JW300: A Wide-Coverage Parallel Corpus for Low-Resource Languages (2019, positive): “The training data is Universal Dependencies version 2.3 (Nivre et al., 2018).”
XLM-E: Cross-lingual Language Model Pre-training via ELECTRA (2021, background): “5 (Zeman et al., 2019), NER named entity recognition on the Wikiann (Pan et al., 2017; Rahimi et al., 2019) dataset, cross-lingual natu-ral language inference on XNLI (Conneau et al., 2018), cross-lingual paraphrase adversaries from word scrambling (PAWS-X; Yang et al. 2019a), and cross-lingual…”
Exploring Fine-tuning Techniques for Pre-trained Cross-lingual Models via Continual Learning (2020, methodology): “For the cross-lingual POS task, we utilize Universal Dependencies 2.0 (Nivre et al., 2017) and choose English (en), French (fr), Spanish (es), Greek (el) and Russian (ru) to evaluate our approaches.”
Small and Practical BERT Models for Sequence Labeling (2019, methodology): “The Meta-LSTM is the best-performing model of the CoNLL 2018 Shared Task (Smith et al., 2018) for universal part-of-speech tagging and morphological features.”
XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation (2021, methodology): “7 treebanks (Nivre et al., 2018) covering 104 languages.”
Explicit Alignment Objectives for Multilingual Bidirectional Encoders (2020, neutral): “3 (Nivre et al., 2018).”
On the Representation Collapse of Sparse Mixture of Experts (2022, background): “5 part-of-speech tagging (Zeman et al., 2019), WikiAnn named entity recognition (Pan et al., 2017; Rahimi et al., 2019), natural language inference (XNLI; Conneau et al. 2018), paraphrase adversaries from word scrambling (PAWS-X; Yang et al. 2019), and question answering on MLQA (Lewis et al.,…”
On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation (2021, background): “Specifically, adapter-based tuning outperforms the reported finetuning results (Hu et al., 2020) on Target and Distant by 2.06% and 3.71% on UD-POS, 1.08% and 0.8% on Wikiann NER, and 0.87% and 0.87% on XNLI.”
BERTje: A Dutch BERT Model (2019, neutral): “5 (Zeman et al., 2019).”
Stanford’s Graph-based Neural Dependency Parser at the CoNLL 2017 Shared Task (2017, methodology): “In this paper, we describe Stanford’s approach to tackling the CoNLL 2017 shared task on Universal Dependency parsing (Nivre et al., 2016; Ze-man et al., 2017; Nivre et al., 2017b,a).”
ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning (2023, neutral): “5) (Zeman et al., 2020).”
MuTual: A Dataset for Multi-Turn Dialogue Reasoning (2020, background): “Moreover, around 10k is sufﬁcient to train a discriminative model (Nivre et al., 2019) or ﬁne-tuning the pre-training model (Wang et al., 2019).”