<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="du-etal-2020-pointing">
    <titleInfo>
        <title>Pointing to Select: A Fast Pointer-LSTM for Long Text Classification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jinhua</namePart>
        <namePart type="family">Du</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yan</namePart>
        <namePart type="family">Huang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Karo</namePart>
        <namePart type="family">Moilanen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 28th International Conference on Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Donia</namePart>
            <namePart type="family">Scott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nuria</namePart>
            <namePart type="family">Bel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Chengqing</namePart>
            <namePart type="family">Zong</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>International Committee on Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Recurrent neural networks (RNNs) suffer from well-known limitations and complications which include slow inference and vanishing gradients when processing long sequences in text classification. Recent studies have attempted to accelerate RNNs via various ad hoc mechanisms to skip irrelevant words in the input. However, word skipping approaches proposed to date effectively stop at each or a given time step to decide whether or not a given input word should be skipped, breaking the coherence of input processing in RNNs. Furthermore, current methods cannot change skip rates during inference and are consequently unable to support different skip rates in demanding real-world conditions. To overcome these limitations, we propose Pointer- LSTM, a novel LSTM framework which relies on a pointer network to select important words for target prediction. The model maintains a coherent input process for the LSTM modules and makes it possible to change the skip rate during inference. Our evaluation on four public data sets demonstrates that Pointer-LSTM (a) is 1.1x∼3.5x faster than the standard LSTM architecture; (b) is more accurate than Leap-LSTM (the state-of-the-art LSTM skipping model) at high skip rates; and (c) reaches robust accuracy levels even when the skip rate is changed during inference.</abstract>
    <identifier type="citekey">du-etal-2020-pointing</identifier>
    <identifier type="doi">10.18653/v1/2020.coling-main.544</identifier>
    <location>
        <url>https://aclanthology.org/2020.coling-main.544</url>
    </location>
    <part>
        <date>2020-12</date>
        <extent unit="page">
            <start>6184</start>
            <end>6193</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Pointing to Select: A Fast Pointer-LSTM for Long Text Classification
%A Du, Jinhua
%A Huang, Yan
%A Moilanen, Karo
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F du-etal-2020-pointing
%X Recurrent neural networks (RNNs) suffer from well-known limitations and complications which include slow inference and vanishing gradients when processing long sequences in text classification. Recent studies have attempted to accelerate RNNs via various ad hoc mechanisms to skip irrelevant words in the input. However, word skipping approaches proposed to date effectively stop at each or a given time step to decide whether or not a given input word should be skipped, breaking the coherence of input processing in RNNs. Furthermore, current methods cannot change skip rates during inference and are consequently unable to support different skip rates in demanding real-world conditions. To overcome these limitations, we propose Pointer- LSTM, a novel LSTM framework which relies on a pointer network to select important words for target prediction. The model maintains a coherent input process for the LSTM modules and makes it possible to change the skip rate during inference. Our evaluation on four public data sets demonstrates that Pointer-LSTM (a) is 1.1x∼3.5x faster than the standard LSTM architecture; (b) is more accurate than Leap-LSTM (the state-of-the-art LSTM skipping model) at high skip rates; and (c) reaches robust accuracy levels even when the skip rate is changed during inference.
%R 10.18653/v1/2020.coling-main.544
%U https://aclanthology.org/2020.coling-main.544
%U https://doi.org/10.18653/v1/2020.coling-main.544
%P 6184-6193

Markdown (Informal)

[Pointing to Select: A Fast Pointer-LSTM for Long Text Classification](https://aclanthology.org/2020.coling-main.544) (Du et al., COLING 2020)

• Pointing to Select: A Fast Pointer-LSTM for Long Text Classification (Du et al., COLING 2020)

ACL

• Jinhua Du, Yan Huang, and Karo Moilanen. 2020. Pointing to Select: A Fast Pointer-LSTM for Long Text Classification. In Proceedings of the 28th International Conference on Computational Linguistics, pages 6184–6193, Barcelona, Spain (Online). International Committee on Computational Linguistics.