@inproceedings{riordan-etal-2019-account,
title = "How to account for mispellings: Quantifying the benefit of character representations in neural content scoring models",
author = "Riordan, Brian and
Flor, Michael and
Pugh, Robert",
editor = "Yannakoudakis, Helen and
Kochmar, Ekaterina and
Leacock, Claudia and
Madnani, Nitin and
Pil{\'a}n, Ildik{\'o} and
Zesch, Torsten",
booktitle = "Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-4411",
doi = "10.18653/v1/W19-4411",
pages = "116--126",
abstract = "Character-based representations in neural models have been claimed to be a tool to overcome spelling variation in in word token-based input. We examine this claim in neural models for content scoring. We formulate precise hypotheses about the possible effects of adding character representations to word-based models and test these hypotheses on large-scale real world content scoring datasets. We find that, while character representations may provide small performance gains in general, their effectiveness in accounting for spelling variation may be limited. We show that spelling correction can provide larger gains than character representations, and that spelling correction improves the performance of models with character representations. With these insights, we report a new state of the art on the ASAP-SAS content scoring dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="riordan-etal-2019-account">
<titleInfo>
<title>How to account for mispellings: Quantifying the benefit of character representations in neural content scoring models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="family">Riordan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Flor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Pugh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Helen</namePart>
<namePart type="family">Yannakoudakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Claudia</namePart>
<namePart type="family">Leacock</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">Ildikó</namePart>
<namePart type="family">Pilán</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">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Character-based representations in neural models have been claimed to be a tool to overcome spelling variation in in word token-based input. We examine this claim in neural models for content scoring. We formulate precise hypotheses about the possible effects of adding character representations to word-based models and test these hypotheses on large-scale real world content scoring datasets. We find that, while character representations may provide small performance gains in general, their effectiveness in accounting for spelling variation may be limited. We show that spelling correction can provide larger gains than character representations, and that spelling correction improves the performance of models with character representations. With these insights, we report a new state of the art on the ASAP-SAS content scoring dataset.</abstract>
<identifier type="citekey">riordan-etal-2019-account</identifier>
<identifier type="doi">10.18653/v1/W19-4411</identifier>
<location>
<url>https://aclanthology.org/W19-4411</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>116</start>
<end>126</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How to account for mispellings: Quantifying the benefit of character representations in neural content scoring models
%A Riordan, Brian
%A Flor, Michael
%A Pugh, Robert
%Y Yannakoudakis, Helen
%Y Kochmar, Ekaterina
%Y Leacock, Claudia
%Y Madnani, Nitin
%Y Pilán, Ildikó
%Y Zesch, Torsten
%S Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F riordan-etal-2019-account
%X Character-based representations in neural models have been claimed to be a tool to overcome spelling variation in in word token-based input. We examine this claim in neural models for content scoring. We formulate precise hypotheses about the possible effects of adding character representations to word-based models and test these hypotheses on large-scale real world content scoring datasets. We find that, while character representations may provide small performance gains in general, their effectiveness in accounting for spelling variation may be limited. We show that spelling correction can provide larger gains than character representations, and that spelling correction improves the performance of models with character representations. With these insights, we report a new state of the art on the ASAP-SAS content scoring dataset.
%R 10.18653/v1/W19-4411
%U https://aclanthology.org/W19-4411
%U https://doi.org/10.18653/v1/W19-4411
%P 116-126
Markdown (Informal)
[How to account for mispellings: Quantifying the benefit of character representations in neural content scoring models](https://aclanthology.org/W19-4411) (Riordan et al., BEA 2019)
ACL