<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jacovi-etal-2018-understanding">
    <titleInfo>
        <title>Understanding Convolutional Neural Networks for Text Classification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Alon</namePart>
        <namePart type="family">Jacovi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Oren</namePart>
        <namePart type="family">Sar Shalom</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yoav</namePart>
        <namePart type="family">Goldberg</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Tal</namePart>
            <namePart type="family">Linzen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Grzegorz</namePart>
            <namePart type="family">Chrupała</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Afra</namePart>
            <namePart type="family">Alishahi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Brussels, Belgium</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We present an analysis into the inner workings of Convolutional Neural Networks (CNNs) for processing text. CNNs used for computer vision can be interpreted by projecting filters into image space, but for discrete sequence inputs CNNs remain a mystery. We aim to understand the method by which the networks process and classify text. We examine common hypotheses to this problem: that filters, accompanied by global max-pooling, serve as ngram detectors. We show that filters may capture several different semantic classes of ngrams by using different activation patterns, and that global max-pooling induces behavior which separates important ngrams from the rest. Finally, we show practical use cases derived from our findings in the form of model interpretability (explaining a trained model by deriving a concrete identity for each filter, bridging the gap between visualization tools in vision tasks and NLP) and prediction interpretability (explaining predictions).</abstract>
    <identifier type="citekey">jacovi-etal-2018-understanding</identifier>
    <identifier type="doi">10.18653/v1/W18-5408</identifier>
    <location>
        <url>https://aclanthology.org/W18-5408</url>
    </location>
    <part>
        <date>2018-11</date>
        <extent unit="page">
            <start>56</start>
            <end>65</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Understanding Convolutional Neural Networks for Text Classification
%A Jacovi, Alon
%A Sar Shalom, Oren
%A Goldberg, Yoav
%Y Linzen, Tal
%Y Chrupała, Grzegorz
%Y Alishahi, Afra
%S Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP
%D 2018
%8 November
%I Association for Computational Linguistics
%C Brussels, Belgium
%F jacovi-etal-2018-understanding
%X We present an analysis into the inner workings of Convolutional Neural Networks (CNNs) for processing text. CNNs used for computer vision can be interpreted by projecting filters into image space, but for discrete sequence inputs CNNs remain a mystery. We aim to understand the method by which the networks process and classify text. We examine common hypotheses to this problem: that filters, accompanied by global max-pooling, serve as ngram detectors. We show that filters may capture several different semantic classes of ngrams by using different activation patterns, and that global max-pooling induces behavior which separates important ngrams from the rest. Finally, we show practical use cases derived from our findings in the form of model interpretability (explaining a trained model by deriving a concrete identity for each filter, bridging the gap between visualization tools in vision tasks and NLP) and prediction interpretability (explaining predictions).
%R 10.18653/v1/W18-5408
%U https://aclanthology.org/W18-5408
%U https://doi.org/10.18653/v1/W18-5408
%P 56-65

Markdown (Informal)

[Understanding Convolutional Neural Networks for Text Classification](https://aclanthology.org/W18-5408) (Jacovi et al., EMNLP 2018)

• Understanding Convolutional Neural Networks for Text Classification (Jacovi et al., EMNLP 2018)

ACL

• Alon Jacovi, Oren Sar Shalom, and Yoav Goldberg. 2018. Understanding Convolutional Neural Networks for Text Classification. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 56–65, Brussels, Belgium. Association for Computational Linguistics.