@inproceedings{jalota-etal-2022-mitigating,
title = "Mitigating Learnerese Effects for {CEFR} Classification",
author = "Jalota, Rricha and
Bourgonje, Peter and
Van Sas, Jan and
Huang, Huiyan",
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-1.3/",
doi = "10.18653/v1/2022.bea-1.3",
pages = "14--21",
abstract = "The role of an author`s L1 in SLA can be challenging for automated CEFR classification, in that texts from different L1 groups may be too heterogeneous to combine them as training data. We experiment with recent debiasing approaches by attempting to devoid textual representations of L1 features. This results in a more homogeneous group when aggregating CEFR-annotated texts from different L1 groups, leading to better classification performance. Using iterative null-space projection, we marginally improve classification performance for a linear classifier by 1 point. An MLP (e.g. non-linear) classifier remains unaffected by this procedure. We discuss possible directions of future work to attempt to increase this performance gain."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jalota-etal-2022-mitigating">
<titleInfo>
<title>Mitigating Learnerese Effects for CEFR Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rricha</namePart>
<namePart type="family">Jalota</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Bourgonje</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Van Sas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huiyan</namePart>
<namePart type="family">Huang</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>The role of an author‘s L1 in SLA can be challenging for automated CEFR classification, in that texts from different L1 groups may be too heterogeneous to combine them as training data. We experiment with recent debiasing approaches by attempting to devoid textual representations of L1 features. This results in a more homogeneous group when aggregating CEFR-annotated texts from different L1 groups, leading to better classification performance. Using iterative null-space projection, we marginally improve classification performance for a linear classifier by 1 point. An MLP (e.g. non-linear) classifier remains unaffected by this procedure. We discuss possible directions of future work to attempt to increase this performance gain.</abstract>
<identifier type="citekey">jalota-etal-2022-mitigating</identifier>
<identifier type="doi">10.18653/v1/2022.bea-1.3</identifier>
<location>
<url>https://aclanthology.org/2022.bea-1.3/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>14</start>
<end>21</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mitigating Learnerese Effects for CEFR Classification
%A Jalota, Rricha
%A Bourgonje, Peter
%A Van Sas, Jan
%A Huang, Huiyan
%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 jalota-etal-2022-mitigating
%X The role of an author‘s L1 in SLA can be challenging for automated CEFR classification, in that texts from different L1 groups may be too heterogeneous to combine them as training data. We experiment with recent debiasing approaches by attempting to devoid textual representations of L1 features. This results in a more homogeneous group when aggregating CEFR-annotated texts from different L1 groups, leading to better classification performance. Using iterative null-space projection, we marginally improve classification performance for a linear classifier by 1 point. An MLP (e.g. non-linear) classifier remains unaffected by this procedure. We discuss possible directions of future work to attempt to increase this performance gain.
%R 10.18653/v1/2022.bea-1.3
%U https://aclanthology.org/2022.bea-1.3/
%U https://doi.org/10.18653/v1/2022.bea-1.3
%P 14-21
Markdown (Informal)
[Mitigating Learnerese Effects for CEFR Classification](https://aclanthology.org/2022.bea-1.3/) (Jalota et al., BEA 2022)
ACL
- Rricha Jalota, Peter Bourgonje, Jan Van Sas, and Huiyan Huang. 2022. Mitigating Learnerese Effects for CEFR Classification. In Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022), pages 14–21, Seattle, Washington. Association for Computational Linguistics.