<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ulmer-etal-2022-exploring">
    <titleInfo>
        <title>Exploring Predictive Uncertainty and Calibration in NLP: A Study on the Impact of Method &amp; Data Scarcity</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Dennis</namePart>
        <namePart type="family">Ulmer</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jes</namePart>
        <namePart type="family">Frellsen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Christian</namePart>
        <namePart type="family">Hardmeier</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yoav</namePart>
            <namePart type="family">Goldberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zornitsa</namePart>
            <namePart type="family">Kozareva</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We investigate the problem of determining the predictive confidence (or, conversely, uncertainty) of a neural classifier through the lens of low-resource languages. By training models on sub-sampled datasets in three different languages, we assess the quality of estimates from a wide array of approaches and their dependence on the amount of available data. We find that while approaches based on pre-trained models and ensembles achieve the best results overall, the quality of uncertainty estimates can surprisingly suffer with more data. We also perform a qualitative analysis of uncertainties on sequences, discovering that a model‘s total uncertainty seems to be influenced to a large degree by its data uncertainty, not model uncertainty. All model implementations are open-sourced in a software package.</abstract>
    <identifier type="citekey">ulmer-etal-2022-exploring</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-emnlp.198</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-emnlp.198/</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>2707</start>
            <end>2735</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Exploring Predictive Uncertainty and Calibration in NLP: A Study on the Impact of Method & Data Scarcity
%A Ulmer, Dennis
%A Frellsen, Jes
%A Hardmeier, Christian
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F ulmer-etal-2022-exploring
%X We investigate the problem of determining the predictive confidence (or, conversely, uncertainty) of a neural classifier through the lens of low-resource languages. By training models on sub-sampled datasets in three different languages, we assess the quality of estimates from a wide array of approaches and their dependence on the amount of available data. We find that while approaches based on pre-trained models and ensembles achieve the best results overall, the quality of uncertainty estimates can surprisingly suffer with more data. We also perform a qualitative analysis of uncertainties on sequences, discovering that a model‘s total uncertainty seems to be influenced to a large degree by its data uncertainty, not model uncertainty. All model implementations are open-sourced in a software package.
%R 10.18653/v1/2022.findings-emnlp.198
%U https://aclanthology.org/2022.findings-emnlp.198/
%U https://doi.org/10.18653/v1/2022.findings-emnlp.198
%P 2707-2735

Markdown (Informal)

[Exploring Predictive Uncertainty and Calibration in NLP: A Study on the Impact of Method & Data Scarcity](https://aclanthology.org/2022.findings-emnlp.198/) (Ulmer et al., Findings 2022)

• Exploring Predictive Uncertainty and Calibration in NLP: A Study on the Impact of Method & Data Scarcity (Ulmer et al., Findings 2022)

ACL

• Dennis Ulmer, Jes Frellsen, and Christian Hardmeier. 2022. Exploring Predictive Uncertainty and Calibration in NLP: A Study on the Impact of Method & Data Scarcity. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 2707–2735, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.