<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="naplava-etal-2021-understanding">
    <titleInfo>
        <title>Understanding Model Robustness to User-generated Noisy Texts</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jakub</namePart>
        <namePart type="family">Náplava</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Martin</namePart>
        <namePart type="family">Popel</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Milan</namePart>
        <namePart type="family">Straka</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jana</namePart>
        <namePart type="family">Straková</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Wei</namePart>
            <namePart type="family">Xu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alan</namePart>
            <namePart type="family">Ritter</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tim</namePart>
            <namePart type="family">Baldwin</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Afshin</namePart>
            <namePart type="family">Rahimi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Sensitivity of deep-neural models to input noise is known to be a challenging problem. In NLP, model performance often deteriorates with naturally occurring noise, such as spelling errors. To mitigate this issue, models may leverage artificially noised data. However, the amount and type of generated noise has so far been determined arbitrarily. We therefore propose to model the errors statistically from grammatical-error-correction corpora. We present a thorough evaluation of several state-of-the-art NLP systems’ robustness in multiple languages, with tasks including morpho-syntactic analysis, named entity recognition, neural machine translation, a subset of the GLUE benchmark and reading comprehension. We also compare two approaches to address the performance drop: a) training the NLP models with noised data generated by our framework; and b) reducing the input noise with external system for natural language correction. The code is released at https://github.com/ufal/kazitext.</abstract>
    <identifier type="citekey">naplava-etal-2021-understanding</identifier>
    <identifier type="doi">10.18653/v1/2021.wnut-1.38</identifier>
    <location>
        <url>https://aclanthology.org/2021.wnut-1.38</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>340</start>
            <end>350</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Understanding Model Robustness to User-generated Noisy Texts
%A Náplava, Jakub
%A Popel, Martin
%A Straka, Milan
%A Straková, Jana
%Y Xu, Wei
%Y Ritter, Alan
%Y Baldwin, Tim
%Y Rahimi, Afshin
%S Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online
%F naplava-etal-2021-understanding
%X Sensitivity of deep-neural models to input noise is known to be a challenging problem. In NLP, model performance often deteriorates with naturally occurring noise, such as spelling errors. To mitigate this issue, models may leverage artificially noised data. However, the amount and type of generated noise has so far been determined arbitrarily. We therefore propose to model the errors statistically from grammatical-error-correction corpora. We present a thorough evaluation of several state-of-the-art NLP systems’ robustness in multiple languages, with tasks including morpho-syntactic analysis, named entity recognition, neural machine translation, a subset of the GLUE benchmark and reading comprehension. We also compare two approaches to address the performance drop: a) training the NLP models with noised data generated by our framework; and b) reducing the input noise with external system for natural language correction. The code is released at https://github.com/ufal/kazitext.
%R 10.18653/v1/2021.wnut-1.38
%U https://aclanthology.org/2021.wnut-1.38
%U https://doi.org/10.18653/v1/2021.wnut-1.38
%P 340-350

Markdown (Informal)

[Understanding Model Robustness to User-generated Noisy Texts](https://aclanthology.org/2021.wnut-1.38) (Náplava et al., WNUT 2021)

• Understanding Model Robustness to User-generated Noisy Texts (Náplava et al., WNUT 2021)

ACL

• Jakub Náplava, Martin Popel, Milan Straka, and Jana Straková. 2021. Understanding Model Robustness to User-generated Noisy Texts. In Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021), pages 340–350, Online. Association for Computational Linguistics.