Automatic coreference resolution is understudied in Danish even though most of the Danish Dependency Treebank (Buch-Kromann, 2003) is annotated with coreference relations.
We present an open-source toolkit for Danish Natural Language Processing, enabling easy access to Danish NLP’s latest advancements.
Corpora of eye movements during reading of contextualized running text is a way of making such records available for natural language processing purposes.
Recent work in cross-topic argument mining attempts to learn models that generalise across topics rather than merely relying on within-topic spurious correlations.
In this paper, we present the first large-scale study of systematically analyzing the potential of EEG brain activity data for improving natural language processing tasks, with a special focus on which features of the signal are most beneficial.
The one-sided focus on English in previous studies of gender bias in NLP misses out on opportunities in other languages: English challenge datasets such as GAP and WinoGender highlight model preferences that are "hallucinatory", e. g., disambiguating gender-ambiguous occurrences of 'doctor' as male doctors.
Large-scale pretrained language models are the major driving force behind recent improvements in performance on the Winograd Schema Challenge, a widely employed test of common sense reasoning ability.
NLP models are imperfect and lack intricate capabilities that humans access automatically when processing speech or reading a text.
We present a named entity annotation for the Danish Universal Dependencies treebank using the CoNLL-2003 annotation scheme: DaNE.
Elazar and Goldberg (2018) showed that protected attributes can be extracted from the representations of a debiased neural network for mention detection at above-chance levels, by evaluating a diagnostic classifier on a held-out subsample of the data it was trained on.
Cognitive language processing data such as eye-tracking features have shown improvements on single NLP tasks.
Learning attention functions requires large volumes of data, but many NLP tasks simulate human behavior, and in this paper, we show that human attention really does provide a good inductive bias on many attention functions in NLP.
We present the first work on predicting reading mistakes in children with reading difficulties based on eye-tracking data from real-world reading teaching.
Even small dictionaries can improve the performance of unsupervised induction algorithms.
Several recent studies have shown that eye movements during reading provide information about grammatical and syntactic processing, which can assist the induction of NLP models.