<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="strubell-etal-2017-fast">
    <titleInfo>
        <title>Fast and Accurate Entity Recognition with Iterated Dilated Convolutions</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Emma</namePart>
        <namePart type="family">Strubell</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Patrick</namePart>
        <namePart type="family">Verga</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">David</namePart>
        <namePart type="family">Belanger</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Andrew</namePart>
        <namePart type="family">McCallum</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Martha</namePart>
            <namePart type="family">Palmer</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rebecca</namePart>
            <namePart type="family">Hwa</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sebastian</namePart>
            <namePart type="family">Riedel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Copenhagen, Denmark</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Today when many practitioners run basic NLP on the entire web and large-volume traffic, faster methods are paramount to saving time and energy costs. Recent advances in GPU hardware have led to the emergence of bi-directional LSTMs as a standard method for obtaining per-token vector representations serving as input to labeling tasks such as NER (often followed by prediction in a linear-chain CRF). Though expressive and accurate, these models fail to fully exploit GPU parallelism, limiting their computational efficiency. This paper proposes a faster alternative to Bi-LSTMs for NER: Iterated Dilated Convolutional Neural Networks (ID-CNNs), which have better capacity than traditional CNNs for large context and structured prediction. Unlike LSTMs whose sequential processing on sentences of length N requires O(N) time even in the face of parallelism, ID-CNNs permit fixed-depth convolutions to run in parallel across entire documents. We describe a distinct combination of network structure, parameter sharing and training procedures that enable dramatic 14-20x test-time speedups while retaining accuracy comparable to the Bi-LSTM-CRF. Moreover, ID-CNNs trained to aggregate context from the entire document are more accurate than Bi-LSTM-CRFs while attaining 8x faster test time speeds.</abstract>
    <identifier type="citekey">strubell-etal-2017-fast</identifier>
    <identifier type="doi">10.18653/v1/D17-1283</identifier>
    <location>
        <url>https://aclanthology.org/D17-1283</url>
    </location>
    <part>
        <date>2017-09</date>
        <extent unit="page">
            <start>2670</start>
            <end>2680</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Fast and Accurate Entity Recognition with Iterated Dilated Convolutions
%A Strubell, Emma
%A Verga, Patrick
%A Belanger, David
%A McCallum, Andrew
%Y Palmer, Martha
%Y Hwa, Rebecca
%Y Riedel, Sebastian
%S Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F strubell-etal-2017-fast
%X Today when many practitioners run basic NLP on the entire web and large-volume traffic, faster methods are paramount to saving time and energy costs. Recent advances in GPU hardware have led to the emergence of bi-directional LSTMs as a standard method for obtaining per-token vector representations serving as input to labeling tasks such as NER (often followed by prediction in a linear-chain CRF). Though expressive and accurate, these models fail to fully exploit GPU parallelism, limiting their computational efficiency. This paper proposes a faster alternative to Bi-LSTMs for NER: Iterated Dilated Convolutional Neural Networks (ID-CNNs), which have better capacity than traditional CNNs for large context and structured prediction. Unlike LSTMs whose sequential processing on sentences of length N requires O(N) time even in the face of parallelism, ID-CNNs permit fixed-depth convolutions to run in parallel across entire documents. We describe a distinct combination of network structure, parameter sharing and training procedures that enable dramatic 14-20x test-time speedups while retaining accuracy comparable to the Bi-LSTM-CRF. Moreover, ID-CNNs trained to aggregate context from the entire document are more accurate than Bi-LSTM-CRFs while attaining 8x faster test time speeds.
%R 10.18653/v1/D17-1283
%U https://aclanthology.org/D17-1283
%U https://doi.org/10.18653/v1/D17-1283
%P 2670-2680

Markdown (Informal)

[Fast and Accurate Entity Recognition with Iterated Dilated Convolutions](https://aclanthology.org/D17-1283) (Strubell et al., EMNLP 2017)

• Fast and Accurate Entity Recognition with Iterated Dilated Convolutions (Strubell et al., EMNLP 2017)

ACL

• Emma Strubell, Patrick Verga, David Belanger, and Andrew McCallum. 2017. Fast and Accurate Entity Recognition with Iterated Dilated Convolutions. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2670–2680, Copenhagen, Denmark. Association for Computational Linguistics.