Result filters

Metadata provider

Language

Resource type

Availability

Active filters:

  • Organisation: Instituut voor de Nederlandse Taal
28 record(s) found

Search results

  • Namescape Visualizer

    Searching and visualizing Named Entities in modern Dutch novels. The named entity (NE) tagging and resolution in NameScape enables quantitative and repeatable research where previously only guesswork and anecdotal evidence was feasible. The visualisation module enables researchers with a less technical background to draw conclusions about functions of names in literary work and help them to explore the material in search of more interesting questions (and answers). Users from other communities (sociolinguistics, sentiment analysis, …) also benefit from the NE tagged data, especially since the NE recognizer is available as a web service, enabling researchers to annotate their own research data. Datasets in NameScape (total of 1.129 books): Corpus Sanders: A corpus of 582 Dutch novels written and published between 1970 and 2009 will. Corpus Huygens: Consists of 22 novels manually tagged with detailed named entity information. IPR for this corpus do not allow distribution. Corpus eBooks: Consists of 7000+ Dutch eBooks tagged automatically with basic NER features and person name Part information. IPR for this corpus do not allow distribution. Corpus SoNaR Books: 105 Dutch books; NE tagged. Corpus Gutenberg Dutch: Consists of 530 NE tagged TEI files converted from the Epub versions of the corresponding Gutenberg documents. Recent research has conclusively proven names in literary works can only be put fully into perspective when studied in a wider context (landscape) of names either in the same text or in related material (the onymic landscape or “namescape”). Research on large corpora is needed to gain a better understanding of e.g. what is characteristic for a certain period, genre, author or cultural region. The data necessary for research on this scale simply does not exist yet. NameScape aims to fill the need by providing a substantial amount of literary works annotated with a rich tag set, thereby enabling researchers to perform their research in more depth than previously possible. Several exploratory visualization tools help the scholar to answer old questions and uncover many more new ones, which can be addressed using the demonstrator.
    de Does, J, Depuydt, K, van Dalen-Oskam, K and Marx, M. 2017. Namescape: Named Entity Recognition from a Literary Perspective. In: Odijk, J and van Hessen, A. (eds.) CLARIN in the Low Countries, Pp. 361–370. London: Ubiquity Press. DOI: https://doi.org/10.5334/bbi.30. License: CC-BY 4.0
    Karina van Dalen-Oskam (2013), Nordic Noir: a background check on Inspector Van Veeteren, 31 May 2012, http://blog.namescape.nl/?p=47

  • Evaluating Repetitions, or how to Improve your Multilingual ASR System by doing Nothing

    A demo of a speech recognizer for POIs (Points of Interest). This demo recognizes stay-over addresses and eateries in some big cities (inter alia Amsterdam, Antwerpen, Gent, Rotterdam).
    This STEVIN project is about the investigation of new pronunciation modeling technologies that can improve the automatic recognition of spoken names in the context of a POI (Point-of-Interest) information providing business service. Collaboration with RU (Nijmegen), UiL (Utrecht), Nuance and TeleAtlas.
    Een demo van een spraakherkenner voor POIs (Points of Interest). Deze demo herkent overnachtingsadressen en eetgelegenheden in enkele grote steden (o.a. Amsterdam, Antwerpen, Gent, Rotterdam).

  • Namescape Barcode Browser

    Searching and visualizing Named Entities in modern Dutch novels. The named entity (NE) tagging and resolution in NameScape enables quantitative and repeatable research where previously only guesswork and anecdotal evidence was feasible. The visualisation module enables researchers with a less technical background to draw conclusions about functions of names in literary work and help them to explore the material in search of more interesting questions (and answers). Users from other communities (sociolinguistics, sentiment analysis, …) also benefit from the NE tagged data, especially since the NE recognizer is available as a web service, enabling researchers to annotate their own research data. Datasets in NameScape (total of 1.129 books): Corpus Sanders: A corpus of 582 Dutch novels written and published between 1970 and 2009 will. Corpus Huygens: Consists of 22 novels manually tagged with detailed named entity information. IPR for this corpus do not allow distribution. Corpus eBooks: Consists of 7000+ Dutch eBooks tagged automatically with basic NER features and person name Part information. IPR for this corpus do not allow distribution. Corpus SoNaR Books: 105 Dutch books; NE tagged. Corpus Gutenberg Dutch: Consists of 530 NE tagged TEI files converted from the Epub versions of the corresponding Gutenberg documents. Recent research has conclusively proven names in literary works can only be put fully into perspective when studied in a wider context (landscape) of names either in the same text or in related material (the onymic landscape or “namescape”). Research on large corpora is needed to gain a better understanding of e.g. what is characteristic for a certain period, genre, author or cultural region. The data necessary for research on this scale simply does not exist yet. NameScape aims to fill the need by providing a substantial amount of literary works annotated with a rich tag set, thereby enabling researchers to perform their research in more depth than previously possible. Several exploratory visualization tools help the scholar to answer old questions and uncover many more new ones, which can be addressed using the demonstrator.
    de Does, J, Depuydt, K, van Dalen-Oskam, K and Marx, M. 2017. Namescape: Named Entity Recognition from a Literary Perspective. In: Odijk, J and van Hessen, A. (eds.) CLARIN in the Low Countries, Pp. 361–370. London: Ubiquity Press. DOI: https://doi.org/10.5334/bbi.30. License: CC-BY 4.0
    Karina van Dalen-Oskam (2013), Nordic Noir: a background check on Inspector Van Veeteren, 31 May 2012, http://blog.namescape.nl/?p=47

  • TiCClops: Text-Induced Corpus Clean-up online processing system

    TICCL (Text Induced Corpus Clean-up) is a system that is designed to search a corpus for all existing variants of (potentially) all words occurring in the corpus. This corpus can be one text, or several, in one or more directories, located on one or more machines. TICCL creates word frequency lists, listing for each word type how often the word occurs in the corpus. These frequencies of the normalized word forms are the sum of the frequencies of the actual word forms found in the corpus. TICCL is a system that is intended to detect and correct typographical errors (misprints) and OCR errors (optical character recognition) in texts. When books or other texts are scanned from paper by a machine, that then turns these scans, i.e. images, into digital text files, errors occur. For instance, the letter combination `in' can be read as `m', and so the word `regeering' is incorrectly reproduced as `regeermg'. TICCL can be used to detect these errors and to suggest a correct form. Text-Induced Corpus Clean-up (TICCL) was developed first as a prototype at the request of the Koninklijke Bibliotheek - The Hague (KB) and reworked into a production tool according to KB specifications (currently at production version 2.0) mainly during the second half of 2008. It is a fully functional environment for processing possibly very large corpora in order to largely remove the undesirable lexical variation in them. It has provisions for various input and output formats, is flexible and robust and has very high recall and acceptable precision. As a spelling variation detection system it is to the developer’s knowledge unique in making principled use of the input text as possible source for target output canonical forms. As such it is far less domain-sensitive than other approaches: the domain is largely covered by the input text collection. TICCL comes in two variants: one with a classic CLAM web application interface, and one with the PhilosTEI interface.
    Reynaert, M. (2008). All, and only, the errors: More complete and consistent spelling and OCR-error correction evaluation. In: Proceedings of the Sixth International Language Resources and Evaluation (LREC’08), Marrakech, Morocco.
    Reynaert, M. (2010). Character confusion versus focus word-based correction of spelling and ocr variants in corpora. International Journal on Document Analysis and Recognition, pp 1-15, URL http://dx.doi.org/10.1007/s10032-010-0133-5

  • user documentation

    Search Application into the collection of all 13th century texts that served as source material for the Early Middle Dutch Dictionary. The source files are available upon request.
    Zoekapplicatie op de verzameling van alle 13e-eeuwse teksten die als bronnenmateriaal hebben gediend voor het Vroegmiddelnederlands Woordenboek. De bronbestanden van het corpus zijn op aanvraag beschikbaar

  • DuELME: Search interface to the Dutch Electronic Lexicon of Multiword Expressions

    The DuELME search interface provides access to the DUELME electronic lexicon, which contains more than 5,000 Dutch multiword expressions (MWEs). MWEs with the same syntactic pattern are grouped in the same equivalence class. The search interface enables users to search for MWEs on the basis of a range of syntactic and semantic criteria, among them expression, pattern id, written form, type, conjugation, polarity, parameters, form, etc. Extensive documentation on the structure of the database is available. DuELME (Dutch Electronic Lexicon of Multiword Expressions) is one of the results of the project Identification and Representation of Multiword Expressions (IRME). The lexical descriptions boast to be highly theory- and implementation-neutral. The DUELME LMF lexicon is suitable for theoretical research on multiword expressions as for use in NLP systems. The DuELME-LMF project has been carried out within the CLARIN-NL programme.
    Grégoire, N. (2009), Untangling Multiword Expressions. A study on the representation and variation of Dutch multiword expressions, PhD thesis, University of Utrecht.

  • OpenConvert

    The OpenConvert tools convert to TEI or FOLiA from a number of input formats (alto, text, word, HTML, ePub). The tools are available as a Java command line tool, a web service and a web application.The OpenConvert Tools were created by IVDNT in the OpenConvert project. The OpenConvert tools convert to TEI or FOLiA from a number of input formats (alto, text, word, HTML, ePub). The tools are available as a Java command line tool, a web service and a web application. Furthermore, as a proof of concept, the website currently provides two annotation tools: a simple Tokenizer for TEI files and a modern Dutch part of speech tagger.
    The tool service can be called as a REST webservice which returns responses in XML, allowing it to be part of a webservice tool chain.
    Input TEI, plain text, HTML
    ALTO XML input
    ePub input
    directory containing files of a valid input type
    zip file (with extension .zip) containing files of a valid input type
    Free for academic use. Non-applicable for commercial parties
    CLARIN based login required. The Clarin federation accepts login from many europian institutions. please seehttp://www.clarin.eu/content/service-provider-federation for more details
    input file name (File upload)
    Format of input file
    Format of output file
    to specify the tagger or tokeniser
    input file mimetype is application/tei+xml
    input file mimetype is text/html
    input file mimetype is text/alto+xml
    input file mimetype is application/msword
    input file mimetype is application/epub+zip
    input file mimetype is text/plain
    output file mimetype is application/tei+xml
    output file mimetype is text/folia+xml
    Basic tagger-lemmatizer for modern Dutch
    a TEI tokenizer

  • WFT-GTB: Integrating the Wurdboek fan ˈe Fryske Taal into the Geïntegreerde TaalBank

    The Dictionary of the Frisian Language (Wurdboek fan de Fryske Taal) is online available via the GTB dictionary web application. The GTB also holds other major Dutch historical dictionaries, such as the Dictionary of Old Dutch (ONW), the Dictionary of early Middle Dutch (VMNW), the Dictionary of Middle Dutch (MNW), and the Dictionary of the Dutch language (WNT). The digital surrounding enables extensive forms of free and structured search queries, including comparative studies with Dutch materials. The Wurdboek fan de Fryske Taal (Dictionary of the Frisian Language)-project includes the vocabulary of Modern West Frisian from the period 1800-1975. The dictionary’s metalanguage is Dutch. A volume of 400 pages comes out every year, the first one in 1984. The editorial phase was finalized in 2009, the final editing and publication phase in 2010.
    Modern Dutch Lemma and Frisian lemma
    Describes the origin of a word
    describes the meaning of a words
    describes the structure of a word
    describes the possible spellings of a word
    Depuydt, K, de Does, J, Duijff, P and Sijens, H. 2017. Making the Dictionary of the Frisian Language Available in the Dutch Historical Dictionary Portal. In: Odijk, J and van Hessen, A. (eds.) CLARIN in the Low Countries, Pp. 151–165. London: Ubiquity Press. DOI: https://doi.org/10.5334/bbi.13. License: CC-BY 4.0

  • Cornetto: Combinatorial and Relational Network as Toolkit for Dutch Language Technology

    Cornetto is a lexical resource for the Dutch language which combines two resources with different semantic organisations: the Dutch Wordnet with its synset organisation and the Dutch Reference Lexicon which includes definitions, usage constraints, selectional restrictions, syntactic behaviours, illustrative contexts, etc. The Cornetto database contains over 92K lemmas and almost 120K word meanings. The Cornetto lexical resource for Dutch covers the most generic and central part of the language. Cornetto combines the structures of the Princeton Wordnet, some of the features from the FrameNet for English and the information on morphological, syntactic, semantic and combinatorial features of lexemes normally found in dictionaries. The Cornetto resource is compiled by combining and aligning two existing semantic resources for Dutch: the Dutch wordnet (DWN) and the Referentie Bestand Nederlands (RBN). Recently, the resource is revised and extended with sentiment values in the From Text to Political Positions project , and with semantic annotations in SONAR, CGN and texts from the Web in the DutchSemCor project. The Cornetto Lexical Resource consists of two large repositories of lexicon data: the lexical entry repository and the synset repository. A Lexical Entry (LE) is a word-meaning pair (i.e. a single meaning of a certain word form), for which morphological, syntactical, semantical and combinatorial information is given. As such, LEs are word senses in the lexical semantic tradition, containing the linguistic knowledge that is needed to properly use the word in a specific meaning in a language. Since the LEs follow a word-to-meaning view, the semantical and combinatorial information for each meaning clarify the differences across the meanings. LEs focus on the polysemy of words and typically follow an approach to represent condensed and generalised meanings from which more specific ones can be derived. Each LE is aligned with a synset (set of synonyms) in the synset repository. As such, a synset can be seen as a set of LEs with the same meaning and every synset stands for a concept. The synsets in Cornetto are interconnected by different semantic relations such as hyponymy, antonymy and meronymy. The Cornet-to Resource is aligned with the English Wordnet, from which domain information was imported. The domains represent clusters of concepts that are related by a shared area of interest, such as sport, education or politics. The definitions of LEs from the same synset should be semantically equivalent and the LEs of a single word form should belong to different synsets. The LEs of a single word form typically differ in terms of connotation, pragmatics, syntax and semantics but synonymous words in the same synset can be differen-tiated along connotation, pragmatics and syntax but not semantics. This structure of the resource makes it possible to combine the very detailed information on form and usage of a specific LE or a group of LEs with the semantic relations which are specified in the corresponding synset(s). For an Open Source version lexico-semantic database for Dutch see the Open Source Dutch Wordnet (ODWN): http://wordpress.let.vupr.nl/odwn/
    Vossen, P., I. maks, R. Segers, H. van der Vliet, M.F. Moens, K. Hofmann, E. Tjong Kim Sang, M. de Rijke (2013), Corntto: a lexical semantic database for Dutch, Chapter in: P. Spyns and J. Odijk (eds): Essential Speech and Language Technology for Dutch, Results by the STEVIN-programme, Publ. Springer series Theory and Applications of Natural Language Processing, ISBN 978-3-642-30909-0.
    Vossen, P., I. Maks, R. Seegers and H. van der Vliet (2008). Integrating Lexical Units, Synsets, and Ontology in the Cornetto Database. In Proceedings of LREC-2008, Marrakech, Morocco.