From Raw Text to Enhanced Universal Dependencies: The Parsing Shared Task at IWPT 2021

Bouma, Gosse; Seddah, Djamé; Zeman, Daniel

doi:10.18653/v1/2021.iwpt-1.15

Cited by 16 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…COMBO took part in IWPT 2021 Shared Task on Parsing into Enhanced Universal Dependencies (Bouma et al, 2021), where it ranked 4th. 4 In addition to ELAS and EULAS metrics, the third evaluation metric was LAS.…”

Section: Combo Performancementioning

confidence: 99%

COMBO: State-of-the-Art Morphosyntactic Analysis

Klimaszewski¹,

Wróblewska²

2021

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations

View full text Add to dashboard Cite

We introduce COMBO -a fully neural NLP system for accurate part-of-speech tagging, morphological analysis, lemmatisation, and (enhanced) dependency parsing. It predicts categorical morphosyntactic features whilst also exposes their vector representations, extracted from hidden layers. COMBO is an easy to install Python package with automatically downloadable pre-trained models for over 40 languages. It maintains a balance between efficiency and quality. As it is an end-to-end system and its modules are jointly trained, its training is competitively fast. As its models are optimised for accuracy, they achieve often better prediction quality than SOTA. The COMBO library is available at: https://gitlab.clarin-pl.eu/ syntactic-tools/combo.

show abstract

Section: Combo Performancementioning

confidence: 99%

COMBO: State-of-the-Art Morphosyntactic Analysis

Klimaszewski¹,

Wróblewska²

2021

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations

View full text Add to dashboard Cite

show abstract

“…Enhanced UD representations have been shown to be useful for downstream NLP tasks (Schuster et al, 2017), and parsing them has experienced a rise of attention in the scope of two recent shared tasks (Bouma et al, 2020(Bouma et al, , 2021). Yet, annota-tions for this dependency representation are still only available for a small subset of UD treebanks.…”

Section: Introductionmentioning

confidence: 99%

“…Parsing into Enhanced UD. Following a series of shared tasks focusing on basic UD (Zeman et al, 2017(Zeman et al, , 2018, the 2020 and 2021 IWPT shared tasks (Bouma et al, 2020(Bouma et al, , 2021 address the prediction of enhanced UD from raw text. While some participating systems directly parse enhanced dependency graphs using a graph-based parser (e.g.…”

Section: Introductionmentioning

confidence: 99%

A Corpus Study of Creating Rule-Based Enhanced Universal Dependencies for German

Bürkle¹,

Grünewald²,

Friedrich³

2021

Proceedings of the Joint 15th Linguistic Annotation Workshop (LAW) and 3rd Designing Meaning Representations (DMR) Workshop

View full text Add to dashboard Cite

In this paper, we present a first attempt at enriching German Universal Dependencies (UD) treebanks with enhanced dependencies. Similarly to the converter for English (Schuster and Manning, 2016), we develop a rule-based system for deriving enhanced dependencies from the basic layer, covering three linguistic phenomena: relative clauses, coordination, and raising/control. For quality control, we manually correct or validate a set of 196 sentences, finding that around 90% of added relations are correct. Our data analysis reveals that difficulties arise mainly due to inconsistencies in the basic layer annotations. We show that the English system is in general applicable to German data, but that adapting to the particularities of the German treebanks and language increases precision and recall by up to 10%. Comparing the application of our converter on gold standard dependencies vs. automatic parses, we find that F1 drops by around 10% in the latter setting due to error propagation. Finally, an enhanced UD parser trained on a converted treebank performs poorly when evaluated against our annotations, indicating that more work remains to be done to create gold standard enhanced German treebanks.

show abstract

“…The IWPT 2020 (Bouma et al, 2020) and 2021 (Bouma et al, 2021) shared tasks focus on parsing into enhanced UD format, where the representation is connected graphs, rather than rooted trees. The extension from trees to graphs allows direct treatment of a wider range of syntactic phenomena, but it also poses a research challenge: how to design parsers suitable for such enhanced UD graphs.…”

Section: Introductionmentioning

confidence: 99%

TGIF: Tree-Graph Integrated-Format Parser for Enhanced UD with Two-Stage Generic- to Individual-Language Finetuning

Shi

Lee

2021

Preprint

View full text Add to dashboard Cite

We present our contribution to the IWPT 2021 shared task on parsing into enhanced Universal Dependencies. Our main system component is a hybrid tree-graph parser that integrates (a) predictions of spanning trees for the enhanced graphs with (b) additional graph edges not present in the spanning trees. We also adopt a finetuning strategy where we first train a language-generic parser on the concatenation of data from all available languages, and then, in a second step, finetune on each individual language separately. Additionally, we develop our own complete set of pre-processing modules relevant to the shared task, including tokenization, sentence segmentation, and multiword token expansion, based on pre-trained XLM-R models and our own pre-training of character-level language models. Our submission reaches a macro-average ELAS of 89.24 on the test set. It ranks top among all teams, with a margin of more than 2 absolute ELAS over the next best-performing submission, and best score on 16 out of 17 languages.

show abstract

From Raw Text to Enhanced Universal Dependencies: The Parsing Shared Task at IWPT 2021

Cited by 16 publications

References 15 publications

COMBO: State-of-the-Art Morphosyntactic Analysis

COMBO: State-of-the-Art Morphosyntactic Analysis

A Corpus Study of Creating Rule-Based Enhanced Universal Dependencies for German

TGIF: Tree-Graph Integrated-Format Parser for Enhanced UD with Two-Stage Generic- to Individual-Language Finetuning

Contact Info

Product

Resources

About