Robbert: a dutch roberta-based language model

P Delobelle, T Winters, B Berendt - arXiv preprint arXiv:2001.06286, 2020 - arxiv.org
Pre-trained language models have been dominating the field of natural language
processing in recent years, and have led to significant performance gains for various …

What the [mask]? making sense of language-specific BERT models

D Nozza, F Bianchi, D Hovy - arXiv preprint arXiv:2003.02912, 2020 - arxiv.org
Recently, Natural Language Processing (NLP) has witnessed an impressive progress in
many areas, due to the advent of novel, pretrained contextual representation models. In …

A comprehensive review on feature set used for anaphora resolution

K Lata, P Singh, K Dutta - Artificial Intelligence Review, 2021 - Springer
Abstract In linguistics, the Anaphora Resolution (AR) is the method of identifying the
antecedent for anaphora. In simple terms, this is the problem that helps to solve what the …

A deep neural network model for speakers coreference resolution in legal texts

D Ji, J Gao, H Fei, C Teng, Y Ren - Information Processing & Management, 2020 - Elsevier
Coreference resolution is one of the fundamental tasks in natural language processing
(NLP), and is of great significance to understand the semantics of texts. Meanwhile …

SICKNL: a dataset for Dutch natural language inference

G Wijnholds, M Moortgat - arXiv preprint arXiv:2101.05716, 2021 - arxiv.org
We present SICK-NL (read: signal), a dataset targeting Natural Language Inference in
Dutch. SICK-NL is obtained by translating the SICK dataset of Marelli et al.(2014) from …

Structural ambiguity and its disambiguation in language model based parsers: the case of dutch clause relativization

G Wijnholds, M Moortgat - arXiv preprint arXiv:2305.14917, 2023 - arxiv.org
This paper addresses structural ambiguity in Dutch relative clauses. By investigating the task
of disambiguation by grounding, we study how the presence of a prior sentence can resolve …

Automatically correcting Dutch pronouns" die" and" dat"

L Allein, A Leeuwenberg, MF Moens - Computational Linguistics in …, 2020 - clinjournal.org
The correct use of Dutch pronouns die and dat is a stumbling block for both native and
nonnative speakers of Dutch due to the multiplicity of syntactic functions and the …

A comparative study of linguistic and computational features based on a machine learning for arabic anaphora resolution

A Abolohom, N Omar, S Pais, J Cordeiro - Procedia Computer Science, 2021 - Elsevier
Anaphora resolution is one of the problems in natural language processing. It is the process
of disambiguating the antecedent of a referring expression from the set of entities in a …

[PDF][PDF] DUTCH DATA AUGMENTATION FOR LOW-RESOURCE TASKS

D Weijden - 2023 - studenttheses.uu.nl
Recent advancements in language models years have resulted in increased performance
on various language task, mostly due to the availability of large datasets for pre-training and …

Resolving Anaphora using Gender and Number Agreement in Marathi text

K Khandale, CN Mahender - … of the International Conference on Data …, 2021 - dl.acm.org
In the area of natural language processing, there is a wide variety of text data available, but
not in the standard format and therefore it is necessary to standardize it. This paper …