Multilingual coreference resolution

Kübler, Sandra; Zhekova, Desislava

doi:10.1111/lnc3.12208

Cited by 3 publications

(3 citation statements)

References 31 publications

(38 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Basic resources for simple semantic role labeling and entity linking were developed during the LORELEI program for many low-resource languages Tracey and Strassel, 2020), including resources for Yoruba and Hausa (even though the latter "fell short" according to the authors). Estonian coreference resolution is targeted by Kübler and Zhekova (2016)…”

Section: B Complexity Of Tasksmentioning

confidence: 99%

A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios

Hedderich¹,

Lange²,

Adel³

et al. 2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

136

View full text Add to dashboard Cite

Deep neural networks and huge language models are becoming omnipresent in natural language applications. As they are known for requiring large amounts of training data, there is a growing body of work to improve the performance in low-resource settings. Motivated by the recent fundamental changes towards neural models and the popular pre-train and fine-tune paradigm, we survey promising approaches for low-resource natural language processing. After a discussion about the different dimensions of data availability, we give a structured overview of methods that enable learning when training data is sparse. This includes mechanisms to create additional labeled data like data augmentation and distant supervision as well as transfer learning settings that reduce the need for target supervision. A goal of our survey is to explain how these methods differ in their requirements as understanding them is essential for choosing a technique suited for a specific low-resource setting. Further key aspects of this work are to highlight open issues and to outline promising directions for future research.

show abstract

Section: B Complexity Of Tasksmentioning

confidence: 99%

A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios

Hedderich¹,

Lange²,

Adel³

et al. 2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

136

View full text Add to dashboard Cite

show abstract

“…However, current language-independent systems were based only on shallow approaches exploiting universal part-of-speech tagset [55] and universal dependencies [56]. Many issues are still unsolved and no system is yet able to handle languagespecific features [57].…”

Section: Multilingual Approachesmentioning

confidence: 99%

ELECTRA for Neural Coreference Resolution in Italian

et al. 2021

View full text Add to dashboard Cite

In recent years, the impact of Neural Language Models has changed every field of Natural Language Processing. In this scenario, coreference resolution has been among the least considered task, especially in language other than English. This work proposes a coreference resolution system for Italian, based on a neural end-to-end architecture integrating ELECTRA language model and trained on OntoCorefIT, a novel Italian dataset built starting from OntoNotes. Even if some approaches for Italian have been proposed in the last decade, to the best of our knowledge, this is the first neural coreference resolver aimed specifically to Italian. The performance of the system is evaluated with respect to three different metrics and also assessed by replacing ELECTRA with the widely-used BERT language model, since its usage has proven to be effective in the coreference resolution task in English. A qualitative analysis has also been conducted, showing how different grammatical categories affect performance in an inflectional and morphological-rich language like Italian. The overall results have shown the effectiveness of the proposed solution, providing a baseline for future developments of this line of research in Italian.

show abstract

“…mentions that, unlike non-referring expressions, could be referred back to in principle, but are not involved in any coreference relations in context. Singletons are important to coreference resolution since they represent true negatives in cluster linking (Kübler and Zhekova, 2011), but also to how humans understand discourse from a theoretical perspective (Grosz et al, 1995), since they also constitute mentioned entities (i.e. clusters of size 1).…”

Section: Introductionmentioning

confidence: 99%

OntoGUM: Evaluating Contextualized SOTA Coreference Resolution on 12 More Genres

Zhu¹,

Pradhan²,

Zeldes³

2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

SOTA coreference resolution produces increasingly impressive scores on the OntoNotes benchmark. However lack of comparable data following the same scheme for more genres makes it difficult to evaluate generalizability to open domain data. This paper provides a dataset and comprehensive evaluation showing that the latest neural LM based end-to-end systems degrade very substantially out of domain. We make an OntoNotes-like coreference dataset called OntoGUM publicly available, converted from GUM, an English corpus covering 12 genres, using deterministic rules, which we evaluate. Thanks to the rich syntactic and discourse annotations in GUM, we are able to create the largest human-annotated coreference corpus following the OntoNotes guidelines, and the first to be evaluated for consistency with the OntoNotes scheme. Outof-domain evaluation across 12 genres shows nearly 15-20% degradation for both deterministic and deep learning systems, indicating a lack of generalizability or covert overfitting in existing coreference resolution models.

show abstract

Multilingual coreference resolution

Cited by 3 publications

References 31 publications

A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios

A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios

ELECTRA for Neural Coreference Resolution in Italian

OntoGUM: Evaluating Contextualized SOTA Coreference Resolution on 12 More Genres

Contact Info

Product

Resources

About