<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="preda-etal-2026-automated">
    <titleInfo>
        <title>Automated Extraction of Answer Candidates for Question Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Claudia</namePart>
        <namePart type="family">Preda</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mihai</namePart>
        <namePart type="family">Dascalu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Stefan</namePart>
        <namePart type="family">Ruseti</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Danielle</namePart>
        <namePart type="given">S</namePart>
        <namePart type="family">McNamara</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>Answering questions based on a reference text is a frequently employed comprehension assessment method that enables teachers to effectively and efficiently evaluate students. Various tools and methods were developed to tackle automated question generation, however, selecting valid answer candidates as a first step is less addressed. Thus, we introduce a solution built on top of FairytaleQA and tailored for training a DeBERTa-based model to classify the quality of each candidate to be part of a strong answer-question pair. First, we extract answer candidates by syntactically parsing the context (i.e., selecting text spans from the reference text based on the nodes in the constituency tree); then, questions are generated for the extracted candidates using a pre-trained LLM model on this task. Next, we assess a candidate’s quality by relying on another fine-tuned model’s capability to answer the previously generated question for that candidate. This enables us to categorize answers using a four-class system: very good, good, average, and unusable. A significant advantage of our method is that the encoder classifier can score all potential answer candidates in a single inference step for the entire context. We compare our selection against both the answers from explicit questions in the original dataset and a fine-tuned LLM for answer selection using an Elo ranking system. In addition, we propose three strategies based on semantic similarity and text position to ensure coverage and diversity of candidates’ selection.</abstract>
    <identifier type="citekey">preda-etal-2026-automated</identifier>
    <identifier type="doi">10.63317/5on33ymypqu7</identifier>
    <location>
        <url>https://aclanthology.org/2026.lrec-1.870/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>11141</start>
            <end>11151</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Automated Extraction of Answer Candidates for Question Generation
%A Preda, Claudia
%A Dascalu, Mihai
%A Ruseti, Stefan
%A McNamara, Danielle S.
%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 preda-etal-2026-automated
%X Answering questions based on a reference text is a frequently employed comprehension assessment method that enables teachers to effectively and efficiently evaluate students. Various tools and methods were developed to tackle automated question generation, however, selecting valid answer candidates as a first step is less addressed. Thus, we introduce a solution built on top of FairytaleQA and tailored for training a DeBERTa-based model to classify the quality of each candidate to be part of a strong answer-question pair. First, we extract answer candidates by syntactically parsing the context (i.e., selecting text spans from the reference text based on the nodes in the constituency tree); then, questions are generated for the extracted candidates using a pre-trained LLM model on this task. Next, we assess a candidate’s quality by relying on another fine-tuned model’s capability to answer the previously generated question for that candidate. This enables us to categorize answers using a four-class system: very good, good, average, and unusable. A significant advantage of our method is that the encoder classifier can score all potential answer candidates in a single inference step for the entire context. We compare our selection against both the answers from explicit questions in the original dataset and a fine-tuned LLM for answer selection using an Elo ranking system. In addition, we propose three strategies based on semantic similarity and text position to ensure coverage and diversity of candidates’ selection.
%R 10.63317/5on33ymypqu7
%U https://aclanthology.org/2026.lrec-1.870/
%U https://doi.org/10.63317/5on33ymypqu7
%P 11141-11151

Markdown (Informal)

[Automated Extraction of Answer Candidates for Question Generation](https://aclanthology.org/2026.lrec-1.870/) (Preda et al., LREC 2026)

• Automated Extraction of Answer Candidates for Question Generation (Preda et al., LREC 2026)

ACL

• Claudia Preda, Mihai Dascalu, Stefan Ruseti, and Danielle S. McNamara. 2026. Automated Extraction of Answer Candidates for Question Generation. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 11141–11151, Palma de Mallorca, Spain. ELRA Language Resource Association.