NT2Lex is a lexical database for Dutch as a foreign language (NT2). The resource includes frequency distributions of words observed in texts graded along the Common European Framework of Reference for Languages (CEFR) scale. It is a receptive lexicon as it includes word frequencies observed in textbook reading activities and simplified readers targeting learners of Dutch.

The resource comes in two versions: a basic version (CGN) and an extended version (CGN+ODWN).

NT2Lex-CGN

The basic version includes 15,227 lexical entries that have been lemmatized and part-of-speech tagged with Frog Tagger. A simplified version of the CGN tagset is used (see resource/cgn_to_nt2lex.yaml).

NT2Lex-CGN+ODWN

The extended version includes 17,743 entries that have been disabmiguated for word senses with the SVM-WSD tool trained on DutchSemCor. Each word sense is also linked to its synset in Open Dutch WordNet.

For each lexical entry, the following linguistic information is given:

• word: the canonical form of the word (lemma)
• tag: the part of speech (simplified CGN tagset)
• sense_se-id: the sense id (if applicable)
• sense_sy-id: the synset id (if applicable)

For each lexical entry appearing at @<cefr_level>, the following corpus statistics are given:

• D: dispersion index
• F: raw frequency
• SFI: standard frequency index
• U: normalized frequency per 1 million words
• tf-idf: term frequency inverse document frequency

Missing values are indicated with a hyphen -.

• search the NT2Lex database
• analyze the lexical complexity of a text with NT2Lex

More information can be found in the following paper. When using the resource(s) in your research or publication, please cite this paper as well.

@inproceedings{tack-etal-2018-nt2lex,
   title = {{NT}2{L}ex: A {CEFR}-Graded Lexical Resource for {D}utch as a Foreign Language Linked to Open {D}utch {W}ord{N}et},
   author = {Tack, Ana{\"\i}s  and
      Fran{\c{c}}ois, Thomas  and
      Desmet, Piet  and
      Fairon, C{\'e}drick},
   booktitle = {Proceedings of the Thirteenth Workshop on Innovative Use of {NLP} for Building Educational Applications},
   month = jun,
   year = {2018},
   address = {New Orleans, Louisiana},
   publisher = {Association for Computational Linguistics},
   url = {https://aclanthology.org/W18-0514},
   doi = {10.18653/v1/W18-0514},
   pages = {137--146}
}

More details can also be found in Chapter 4 of my Ph.D. thesis.

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

See LICENSE.txt for more details.

All notable changes to this project will be documented in this file.

The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.

Added

• First release of the resource