@inproceedings{goncalves-etal-2026-luxdiagrc,
title = "{L}ux{D}iag{RC}: A Diagnostic Reading Comprehension Corpus for {L}uxembourgish with Linguistic and Cognitive Annotation Layers",
author = "Gon{\c{c}}alves, Christophe Friezas and
Lamsiyah, Salima and
Schommer, Christoph",
editor = "Hettiarachchi, Hansi and
Ranasinghe, Tharindu and
Plum, Alistair and
Rayson, Paul and
Mitkov, Ruslan and
Gaber, Mohamed and
Premasiri, Damith and
Tan, Fiona Anting and
Uyangodage, Lasitha",
booktitle = "Proceedings of the Second Workshop on Language Models for Low-Resource Languages ({L}o{R}es{LM} 2026)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.loreslm-1.46/",
pages = "532--541",
ISBN = "979-8-89176-377-7",
abstract = "Reading comprehension resources for low-resource languages remain limited, particularly datasets designed for educational assessment and diagnostic analysis in contrast to binary correctness.We present a diagnostically rich reading comprehension corpus forLuxembourgish, annotated using a two-layer framework that separateslinguistic sources of textual difficulty from cognitive and diagnosticproperties of comprehension questions. The linguistic layer captures span-level lexical, syntactic, morphological, and discourse-related features, while the cognitive layerannotates multiple-choice questions according to the PIRLS cognitiveprocesses and diagnostically meaningful distractor types following theSTARC framework.This design enables fine-grained analysis of reading comprehensionerrors by linking response patterns to underlying linguistic phenomena. The resulting corpus consists of 640 multiple-choice questions based on 16 annotated Luxembourgish texts. We describe the annotation methodology agreement measures, and will releasethe dataset as a publicly available resource for educational andlow-resource NLP research."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="goncalves-etal-2026-luxdiagrc">
<titleInfo>
<title>LuxDiagRC: A Diagnostic Reading Comprehension Corpus for Luxembourgish with Linguistic and Cognitive Annotation Layers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christophe</namePart>
<namePart type="given">Friezas</namePart>
<namePart type="family">Gonçalves</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salima</namePart>
<namePart type="family">Lamsiyah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christoph</namePart>
<namePart type="family">Schommer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Language Models for Low-Resource Languages (LoResLM 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hansi</namePart>
<namePart type="family">Hettiarachchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alistair</namePart>
<namePart type="family">Plum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Gaber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damith</namePart>
<namePart type="family">Premasiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fiona</namePart>
<namePart type="given">Anting</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lasitha</namePart>
<namePart type="family">Uyangodage</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-377-7</identifier>
</relatedItem>
<abstract>Reading comprehension resources for low-resource languages remain limited, particularly datasets designed for educational assessment and diagnostic analysis in contrast to binary correctness.We present a diagnostically rich reading comprehension corpus forLuxembourgish, annotated using a two-layer framework that separateslinguistic sources of textual difficulty from cognitive and diagnosticproperties of comprehension questions. The linguistic layer captures span-level lexical, syntactic, morphological, and discourse-related features, while the cognitive layerannotates multiple-choice questions according to the PIRLS cognitiveprocesses and diagnostically meaningful distractor types following theSTARC framework.This design enables fine-grained analysis of reading comprehensionerrors by linking response patterns to underlying linguistic phenomena. The resulting corpus consists of 640 multiple-choice questions based on 16 annotated Luxembourgish texts. We describe the annotation methodology agreement measures, and will releasethe dataset as a publicly available resource for educational andlow-resource NLP research.</abstract>
<identifier type="citekey">goncalves-etal-2026-luxdiagrc</identifier>
<location>
<url>https://aclanthology.org/2026.loreslm-1.46/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>532</start>
<end>541</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LuxDiagRC: A Diagnostic Reading Comprehension Corpus for Luxembourgish with Linguistic and Cognitive Annotation Layers
%A Gonçalves, Christophe Friezas
%A Lamsiyah, Salima
%A Schommer, Christoph
%Y Hettiarachchi, Hansi
%Y Ranasinghe, Tharindu
%Y Plum, Alistair
%Y Rayson, Paul
%Y Mitkov, Ruslan
%Y Gaber, Mohamed
%Y Premasiri, Damith
%Y Tan, Fiona Anting
%Y Uyangodage, Lasitha
%S Proceedings of the Second Workshop on Language Models for Low-Resource Languages (LoResLM 2026)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-377-7
%F goncalves-etal-2026-luxdiagrc
%X Reading comprehension resources for low-resource languages remain limited, particularly datasets designed for educational assessment and diagnostic analysis in contrast to binary correctness.We present a diagnostically rich reading comprehension corpus forLuxembourgish, annotated using a two-layer framework that separateslinguistic sources of textual difficulty from cognitive and diagnosticproperties of comprehension questions. The linguistic layer captures span-level lexical, syntactic, morphological, and discourse-related features, while the cognitive layerannotates multiple-choice questions according to the PIRLS cognitiveprocesses and diagnostically meaningful distractor types following theSTARC framework.This design enables fine-grained analysis of reading comprehensionerrors by linking response patterns to underlying linguistic phenomena. The resulting corpus consists of 640 multiple-choice questions based on 16 annotated Luxembourgish texts. We describe the annotation methodology agreement measures, and will releasethe dataset as a publicly available resource for educational andlow-resource NLP research.
%U https://aclanthology.org/2026.loreslm-1.46/
%P 532-541
Markdown (Informal)
[LuxDiagRC: A Diagnostic Reading Comprehension Corpus for Luxembourgish with Linguistic and Cognitive Annotation Layers](https://aclanthology.org/2026.loreslm-1.46/) (Gonçalves et al., LoResLM 2026)
ACL