@inproceedings{laarmann-quante-etal-2022-meet,
title = "{\textquoteleft}Meet me at the ribary' {--} Acceptability of spelling variants in free-text answers to listening comprehension prompts",
author = "Laarmann-Quante, Ronja and
Schwarz, Leska and
Horbach, Andrea and
Zesch, Torsten",
editor = {Kochmar, Ekaterina and
Burstein, Jill and
Horbach, Andrea and
Laarmann-Quante, Ronja and
Madnani, Nitin and
Tack, Ana{\"i}s and
Yaneva, Victoria and
Yuan, Zheng and
Zesch, Torsten},
booktitle = "Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022)",
month = jul,
year = "2022",
address = "Seattle, Washington",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.bea-1.22/",
doi = "10.18653/v1/2022.bea-1.22",
pages = "173--182",
abstract = "When listening comprehension is tested as a free-text production task, a challenge for scoring the answers is the resulting wide range of spelling variants. When judging whether a variant is acceptable or not, human raters perform a complex holistic decision. In this paper, we present a corpus study in which we analyze human acceptability decisions in a high stakes test for German. We show that for human experts, spelling variants are harder to score consistently than other answer variants. Furthermore, we examine how the decision can be operationalized using features that could be applied by an automatic scoring system. We show that simple measures like edit distance and phonetic similarity between a given answer and the target answer can model the human acceptability decisions with the same inter-annotator agreement as humans, and discuss implications of the remaining inconsistencies."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="laarmann-quante-etal-2022-meet">
<titleInfo>
<title>‘Meet me at the ribary’ – Acceptability of spelling variants in free-text answers to listening comprehension prompts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ronja</namePart>
<namePart type="family">Laarmann-Quante</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leska</namePart>
<namePart type="family">Schwarz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Horbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Torsten</namePart>
<namePart type="family">Zesch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Horbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ronja</namePart>
<namePart type="family">Laarmann-Quante</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nitin</namePart>
<namePart type="family">Madnani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anaïs</namePart>
<namePart type="family">Tack</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="family">Yaneva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Torsten</namePart>
<namePart type="family">Zesch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, Washington</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>When listening comprehension is tested as a free-text production task, a challenge for scoring the answers is the resulting wide range of spelling variants. When judging whether a variant is acceptable or not, human raters perform a complex holistic decision. In this paper, we present a corpus study in which we analyze human acceptability decisions in a high stakes test for German. We show that for human experts, spelling variants are harder to score consistently than other answer variants. Furthermore, we examine how the decision can be operationalized using features that could be applied by an automatic scoring system. We show that simple measures like edit distance and phonetic similarity between a given answer and the target answer can model the human acceptability decisions with the same inter-annotator agreement as humans, and discuss implications of the remaining inconsistencies.</abstract>
<identifier type="citekey">laarmann-quante-etal-2022-meet</identifier>
<identifier type="doi">10.18653/v1/2022.bea-1.22</identifier>
<location>
<url>https://aclanthology.org/2022.bea-1.22/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>173</start>
<end>182</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ‘Meet me at the ribary’ – Acceptability of spelling variants in free-text answers to listening comprehension prompts
%A Laarmann-Quante, Ronja
%A Schwarz, Leska
%A Horbach, Andrea
%A Zesch, Torsten
%Y Kochmar, Ekaterina
%Y Burstein, Jill
%Y Horbach, Andrea
%Y Laarmann-Quante, Ronja
%Y Madnani, Nitin
%Y Tack, Anaïs
%Y Yaneva, Victoria
%Y Yuan, Zheng
%Y Zesch, Torsten
%S Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022)
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, Washington
%F laarmann-quante-etal-2022-meet
%X When listening comprehension is tested as a free-text production task, a challenge for scoring the answers is the resulting wide range of spelling variants. When judging whether a variant is acceptable or not, human raters perform a complex holistic decision. In this paper, we present a corpus study in which we analyze human acceptability decisions in a high stakes test for German. We show that for human experts, spelling variants are harder to score consistently than other answer variants. Furthermore, we examine how the decision can be operationalized using features that could be applied by an automatic scoring system. We show that simple measures like edit distance and phonetic similarity between a given answer and the target answer can model the human acceptability decisions with the same inter-annotator agreement as humans, and discuss implications of the remaining inconsistencies.
%R 10.18653/v1/2022.bea-1.22
%U https://aclanthology.org/2022.bea-1.22/
%U https://doi.org/10.18653/v1/2022.bea-1.22
%P 173-182
Markdown (Informal)
[‘Meet me at the ribary’ – Acceptability of spelling variants in free-text answers to listening comprehension prompts](https://aclanthology.org/2022.bea-1.22/) (Laarmann-Quante et al., BEA 2022)
ACL