<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jain-etal-2022-influence">
    <titleInfo>
        <title>Influence Functions for Sequence Tagging Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sarthak</namePart>
        <namePart type="family">Jain</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Varun</namePart>
        <namePart type="family">Manjunatha</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Byron</namePart>
        <namePart type="family">Wallace</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ani</namePart>
        <namePart type="family">Nenkova</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>Many standard tasks in NLP (e.g., Named Entity Recognition, Part-of-Speech tagging, and Semantic Role Labeling) are naturally framed as sequence tagging problems. However, there has been comparatively little work on interpretability methods for sequence tagging models. In this paper, we extend influence functions — which aim to trace predictions back to the training points that informed them — to sequence tagging tasks. We define the influence of a training instance segment as the effect that perturbing the labels within this segment has on a test segment level prediction. We provide an efficient approximation to compute this, and show that it tracks with the “true” segment influence (measured empirically). We show the practical utility of segment influence by using the method to identify noisy annotations in NER corpora.</abstract>
    <identifier type="citekey">jain-etal-2022-influence</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-emnlp.58</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-emnlp.58/</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>824</start>
            <end>839</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Influence Functions for Sequence Tagging Models
%A Jain, Sarthak
%A Manjunatha, Varun
%A Wallace, Byron
%A Nenkova, Ani
%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 jain-etal-2022-influence
%X Many standard tasks in NLP (e.g., Named Entity Recognition, Part-of-Speech tagging, and Semantic Role Labeling) are naturally framed as sequence tagging problems. However, there has been comparatively little work on interpretability methods for sequence tagging models. In this paper, we extend influence functions — which aim to trace predictions back to the training points that informed them — to sequence tagging tasks. We define the influence of a training instance segment as the effect that perturbing the labels within this segment has on a test segment level prediction. We provide an efficient approximation to compute this, and show that it tracks with the “true” segment influence (measured empirically). We show the practical utility of segment influence by using the method to identify noisy annotations in NER corpora.
%R 10.18653/v1/2022.findings-emnlp.58
%U https://aclanthology.org/2022.findings-emnlp.58/
%U https://doi.org/10.18653/v1/2022.findings-emnlp.58
%P 824-839

Markdown (Informal)

[Influence Functions for Sequence Tagging Models](https://aclanthology.org/2022.findings-emnlp.58/) (Jain et al., Findings 2022)

• Influence Functions for Sequence Tagging Models (Jain et al., Findings 2022)

ACL

• Sarthak Jain, Varun Manjunatha, Byron Wallace, and Ani Nenkova. 2022. Influence Functions for Sequence Tagging Models. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 824–839, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.