<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rei-sogaard-2018-zero">
    <titleInfo>
        <title>Zero-Shot Sequence Labeling: Transferring Knowledge from Sentences to Tokens</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Marek</namePart>
        <namePart type="family">Rei</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Anders</namePart>
        <namePart type="family">Søgaard</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marilyn</namePart>
            <namePart type="family">Walker</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Heng</namePart>
            <namePart type="family">Ji</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Amanda</namePart>
            <namePart type="family">Stent</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">New Orleans, Louisiana</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Can attention- or gradient-based visualization techniques be used to infer token-level labels for binary sequence tagging problems, using networks trained only on sentence-level labels? We construct a neural network architecture based on soft attention, train it as a binary sentence classifier and evaluate against token-level annotation on four different datasets. Inferring token labels from a network provides a method for quantitatively evaluating what the model is learning, along with generating useful feedback in assistance systems. Our results indicate that attention-based methods are able to predict token-level labels more accurately, compared to gradient-based methods, sometimes even rivaling the supervised oracle network.</abstract>
    <identifier type="citekey">rei-sogaard-2018-zero</identifier>
    <identifier type="doi">10.18653/v1/N18-1027</identifier>
    <location>
        <url>https://aclanthology.org/N18-1027</url>
    </location>
    <part>
        <date>2018-06</date>
        <extent unit="page">
            <start>293</start>
            <end>302</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Zero-Shot Sequence Labeling: Transferring Knowledge from Sentences to Tokens
%A Rei, Marek
%A Søgaard, Anders
%Y Walker, Marilyn
%Y Ji, Heng
%Y Stent, Amanda
%S Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)
%D 2018
%8 June
%I Association for Computational Linguistics
%C New Orleans, Louisiana
%F rei-sogaard-2018-zero
%X Can attention- or gradient-based visualization techniques be used to infer token-level labels for binary sequence tagging problems, using networks trained only on sentence-level labels? We construct a neural network architecture based on soft attention, train it as a binary sentence classifier and evaluate against token-level annotation on four different datasets. Inferring token labels from a network provides a method for quantitatively evaluating what the model is learning, along with generating useful feedback in assistance systems. Our results indicate that attention-based methods are able to predict token-level labels more accurately, compared to gradient-based methods, sometimes even rivaling the supervised oracle network.
%R 10.18653/v1/N18-1027
%U https://aclanthology.org/N18-1027
%U https://doi.org/10.18653/v1/N18-1027
%P 293-302

Markdown (Informal)

[Zero-Shot Sequence Labeling: Transferring Knowledge from Sentences to Tokens](https://aclanthology.org/N18-1027) (Rei & Søgaard, NAACL 2018)

• Zero-Shot Sequence Labeling: Transferring Knowledge from Sentences to Tokens (Rei & Søgaard, NAACL 2018)

ACL

• Marek Rei and Anders Søgaard. 2018. Zero-Shot Sequence Labeling: Transferring Knowledge from Sentences to Tokens. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 293–302, New Orleans, Louisiana. Association for Computational Linguistics.