Dutch Named Entity Recognition and De-Identification Methods for the Human Resource Domain

The human resource (HR) domain contains various types of privacy-sensitive textual data, such as e-mail correspondence and performance appraisal. Doing research on these documents brings several challenges, one of them anonymisation. In this paper, we evaluate the current Dutch text de-identification methods for the HR domain in four steps. First, by updating one of these methods with the latest named entity recognition (NER) models. The result is that the NER model based on the CoNLL 2002 corpus in combination with the BERTje transformer give the best combination for suppressing persons (recall 0.94) and locations (recall 0.82). For suppressing gender, DEDUCE is performing best (recall 0.53). Second NER evaluation is based on both strict de-identification of entities (a person must be suppressed as a person) and third evaluation on a loose sense of de-identification (no matter what how a person is suppressed, as long it is suppressed). In the fourth and last step a new kind of NER dataset is tested for recognising job titles in tezts.

Evaluating Dutch Named Entity Recognition and De-Identification Methods in the Human Resource Domain

The human resource (HR) domain contains various types of privacy-sensitive textual data, such as e-mail correspondence and performance appraisal. Doing research on these documents brings several challenges, one of them anonymisation. In this paper, we evaluate the current Dutch text de-identification methods for the HR domain in three steps. First, by updating one of these methods with the latest named entity recognition (NER) models. The result is that the NER model based on the CoNLL 2002 corpus in combination with the BERTje transformer give the best combination for suppressing persons (recall 0.94) and locations (recall 0.82). For suppressing gender, DEDUCE is performing best (recall 0.53). Second NER evaluation is based on both strict de-identification of entities (a person must be suppressed as a person) and third evaluation on a loose sense of de-identification (no matter what how a person is suppressed, as long it is suppressed).

Vissen naar variatie : Digitaal op zoek naar onbekende Noord/Zuid-verschillen in de grammatica van het Nederlands

Belgian Dutch (BD) and Netherlandic Dutch (ND) are known to exhibit phonetic and lexical differences, but national variation in the syntax of Dutch has often been claimed to be quasi non-existent. This view is rooted in the fact that both laypersons and researchers are oblivious to national divergences in the grammar of Dutch (unless they are categorical and/or heavily mediatized), but also in the undisputed belief that BD and ND are different surface manifestations of ‘the same grammatical motor’. As a result, only a few syntactic phenomena have hitherto been shown to be sensitive to national constraints. In this paper we illustrate a computational bottom-up approach (pioneered in Bannard & Callison-Burch 2005) to cast the net as widely as possible. Building on statistical machine translation and a parallel corpus of Dutch translations of English subtitles, we identify plausible mappings between English n-grams and their Dutch translations. We do this in order to obtain paraphrases, i.e., stretches of interchangeable Dutch text that carry approximately the same meaning. In a first case study, we found corroborating evidence among the discovered paraphrases for many syntactic variables that have previously been attested in Dutch, including complementizer variation, existential er-variation, word order phenomena, and inflection variation. Crucially, we also discovered a number of alternations we had not anticipated as interesting variables. In order to detect national constraints on the newly found variables, we carried out a second experiment with a smaller corpus of Belgian and Netherlandic subtitles: the two variables we investigated in this light ‐ deictic strength variation and subordination variation ‐ did indeed manifest national sensitivity.

Presencia de Saavedra Fajardo en un libro de emblemas neerlandés

ABSTRACT:In 1668, the emblem bookHet voorhof der ziele[The Antechamber of the Soul] was published in Rotterdam by the bookseller and humanist François van Hoogstraten. Its main argument conveys the concept of vanitas, since its point of departure is found in the Tratado de La Vanidad del mundo(Treatise of the Vanity of the World) by the Spanish preacher, friar Diego de Estella (1574). This work, rather than slavishly following the sources and content of the Spanish treatise, includes a series of variants that allow for the corroboration that it is neither plagiarism nor a translation of the Spanish original. These variant include the incorporation of works subsequent to the publication of Estella's work. o this end, the introduction of numerous quotations of the emblematist Diego Saavedra Fajardo is significant. The aim of this work is to carry out an analysis of the presence of the diplomat from Murcia in the Dutch text to determine the reasons that led Hoogstraten to introduce in his repertoire the most important Spanish emblematist of the Modern Age. KEYWORDS: Emblematics; Modern Age; François van Hoogstraten; Diego de Estella; Diego Saavedra Fajardo; Vanity. RESUMEN:En 1668 vio la luz en Róterdam Het voorhof der ziele[Antesala del Alma], un libro de emblemas publicado por el librero y humanista François van Hoogstraten, cuyo argumento principal transmite el concepto de vanitas,ya que su punto de partida se sitúa en el Tratado deLa Vanidad del mundo del predicador español fray Diego de Estella (1574). La obra, más allá de seguir casi al pie de la letra las fuentes y contenidos recogidos en el tratado español, posee una serie de variantes que permiten corroborar que no se trata ni de un plagio ni de una traducción del mismo, tales como la incorporación de obras posteriores a su publicación. En este sentido, resulta significativa la introducción de numerosas citas del emblemista Diego Saavedra Fajardo. El propósito de este trabajo es realizar un análisis de la presencia del diplomático murciano en el texto neerlandés para determinar los motivos que llevaron a Hoogstraten a introducir en su repertorio al emblemista español más importante de la Edad Moderna. PALABRAS CLAVES: emblemática; Edad Moderna; François van Hoogstraten; Diego de Estella; Diego Saavedra Fajardo; vanitas.

De Spiegel historiael in Italië: onbekende fragmenten te Valenza

The public library of Valenza, in the Italian region of Piedmont, holds two parchment fragments of Jacob van Maerlant’s Spiegel historiael which are used to protect other documents. The present paper is the first study dedicated to them. The leaves are first described separately, highlighting their shape as well as the text which has been handed down to us. Taking into account paleographical, ortho-graphical and linguistic aspects, the author tries to reconstruct the original manu-script from which both fragments derive, reaching the conclusion that it was writ-ten in the first quarter of the 14th century in the area of (South-)Eastern Flanders or Western Brabant. Furthermore, special attention is paid to the hypothesis that the fragments reached Piedmont because of the strong presence in the Low Countries of Italian money lenders, the so called ‘Lombards’, who came exactly from that re-gion. The complete edition of the Middle Dutch text, followed by notes, concludes the study.

Korte inleiding in gedragsverandering

This is a Dutch text with an accessible introduction to the dynamics of behavior change, originally written for MAMDT students of the Hogeschool Zuyd for their Party Panel project.

Comedy and Biography in the Reckless Student (Anonymous, 1681) (Schwankhaftes und Biographisches im Ruchlosen Studenten (anonym, 1681))

This essay discusses the transformation and breakdown of the picaresque in the late 17th century, with specific reference to narrative strategies used in Der ruchlose Student (1681), an anonymous and fragmentary German translation of a Dutch text – picaresque in the broader sense. These strategies, it is argued, reveal both an internalisation of the first-person narrator and early manifestations of a causally motivated (biographical) syntagma. By way of example, it is demonstrated how the typical affectively flat, villainous narrator of earlier picaresque novels, as well as the episodic structure of these texts, are transformed in Der ruchlose Student such as to enable the emergence of a more modern individual within the framework of a more consistent story line. As such, this essay contributes indirectly to scholarly discussions relating to the embourgeoisement of the picaro figure. Der folgende Text stellt einen Beitrag zu Um- und Abbauten des Pikaresken gegen Ende des 17. Jahrhunderts dar. Er widmet sich den narrativen Strategien in dem anonym verfassten Romanfragment Der ruchlose Student (1681), der deutschen Übersetzung eines niederländischen Schelmenromans im weiteren Sinne, die eine Verinnerlichung des pikaresken Ich-Erzählers sowie erste Ausprägungen eines kausal motivierten (biographischen) Syntagmas erkennen lassen. Exemplarisch wird also herausgearbeitet, wie sich der typische pikareske statische Erzähler älterer Schelmenromane sowie deren episodische Handlungsführung in Ansätzen transformieren und ein moderneres Individuum in einem konsistenteren Handlungsgefüge aufscheint. Indirekt schließt der Beitrag damit an die Debatte um die Verbürgerlichung des Pikaros an.