@inproceedings{van-hee-etal-2026-textlens,
title = "{T}ext{L}ens {\&} {L}e{TT}uce: Automated Corpus Annotation and Multilingual Tagging as a Service",
author = "Van Hee, Cynthia and
Doumen, Jonas and
Prins, Vincent and
Singh, Pranaydeep and
Vandeghinste, Vincent and
Lefever, Els",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.906/",
doi = "10.63317/3jvno99c6y49",
pages = "11574--11584",
abstract = "We present TextLens, a web-based platform for automated linguistic annotation designed to lower technical barriers for researchers in digital humanities, linguistics and translation studies. Hosted by the Dutch Language Institute (INT), TextLens allows users to upload and annotate corpora in a variety of formats (.txt, .tsv, CoNLL-U, FoLiA, TEI, and NAF) using state-of-the-art NLP tools, without the need for local installation or computational resources. The platform supports multilingual data processing and provides a persistent dashboard for managing, monitoring and sharing annotation projects. Alongside this service, we introduce the LeTTuce-PoS Dataset, a new multilingual, manually annotated dataset for part-of-speech tagging in English, French, Dutch and German, covering multiple genres and offering a valuable resource to the research community. This paper also reports benchmark results for different PoS taggers (LeTs Preprocess, LeTTuce, spaCy and Stanza) on the dataset. Together, TextLens and the LeTTuce-PoS Dataset provide an accessible, scalable platform for high-quality annotation and a robust multilingual dataset that support comparable and reproducible research in multilingual contexts."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="van-hee-etal-2026-textlens">
<titleInfo>
<title>TextLens & LeTTuce: Automated Corpus Annotation and Multilingual Tagging as a Service</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cynthia</namePart>
<namePart type="family">Van Hee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonas</namePart>
<namePart type="family">Doumen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Prins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pranaydeep</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Vandeghinste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Els</namePart>
<namePart type="family">Lefever</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present TextLens, a web-based platform for automated linguistic annotation designed to lower technical barriers for researchers in digital humanities, linguistics and translation studies. Hosted by the Dutch Language Institute (INT), TextLens allows users to upload and annotate corpora in a variety of formats (.txt, .tsv, CoNLL-U, FoLiA, TEI, and NAF) using state-of-the-art NLP tools, without the need for local installation or computational resources. The platform supports multilingual data processing and provides a persistent dashboard for managing, monitoring and sharing annotation projects. Alongside this service, we introduce the LeTTuce-PoS Dataset, a new multilingual, manually annotated dataset for part-of-speech tagging in English, French, Dutch and German, covering multiple genres and offering a valuable resource to the research community. This paper also reports benchmark results for different PoS taggers (LeTs Preprocess, LeTTuce, spaCy and Stanza) on the dataset. Together, TextLens and the LeTTuce-PoS Dataset provide an accessible, scalable platform for high-quality annotation and a robust multilingual dataset that support comparable and reproducible research in multilingual contexts.</abstract>
<identifier type="citekey">van-hee-etal-2026-textlens</identifier>
<identifier type="doi">10.63317/3jvno99c6y49</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.906/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>11574</start>
<end>11584</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TextLens & LeTTuce: Automated Corpus Annotation and Multilingual Tagging as a Service
%A Van Hee, Cynthia
%A Doumen, Jonas
%A Prins, Vincent
%A Singh, Pranaydeep
%A Vandeghinste, Vincent
%A Lefever, Els
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F van-hee-etal-2026-textlens
%X We present TextLens, a web-based platform for automated linguistic annotation designed to lower technical barriers for researchers in digital humanities, linguistics and translation studies. Hosted by the Dutch Language Institute (INT), TextLens allows users to upload and annotate corpora in a variety of formats (.txt, .tsv, CoNLL-U, FoLiA, TEI, and NAF) using state-of-the-art NLP tools, without the need for local installation or computational resources. The platform supports multilingual data processing and provides a persistent dashboard for managing, monitoring and sharing annotation projects. Alongside this service, we introduce the LeTTuce-PoS Dataset, a new multilingual, manually annotated dataset for part-of-speech tagging in English, French, Dutch and German, covering multiple genres and offering a valuable resource to the research community. This paper also reports benchmark results for different PoS taggers (LeTs Preprocess, LeTTuce, spaCy and Stanza) on the dataset. Together, TextLens and the LeTTuce-PoS Dataset provide an accessible, scalable platform for high-quality annotation and a robust multilingual dataset that support comparable and reproducible research in multilingual contexts.
%R 10.63317/3jvno99c6y49
%U https://aclanthology.org/2026.lrec-1.906/
%U https://doi.org/10.63317/3jvno99c6y49
%P 11574-11584
Markdown (Informal)
[TextLens & LeTTuce: Automated Corpus Annotation and Multilingual Tagging as a Service](https://aclanthology.org/2026.lrec-1.906/) (Van Hee et al., LREC 2026)
ACL