<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="marecek-rosa-2018-extracting">
    <titleInfo>
        <title>Extracting Syntactic Trees from Transformer Encoder Self-Attentions</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">David</namePart>
        <namePart type="family">Mareček</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rudolf</namePart>
        <namePart type="family">Rosa</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>This is a work in progress about extracting the sentence tree structures from the encoder’s self-attention weights, when translating into another language using the Transformer neural network architecture. We visualize the structures and discuss their characteristics with respect to the existing syntactic theories and annotations.</abstract>
    <identifier type="citekey">marecek-rosa-2018-extracting</identifier>
    <identifier type="doi">10.18653/v1/W18-5444</identifier>
    <location>
        <url>https://aclanthology.org/W18-5444</url>
    </location>
    <part>
        <date>2018-11</date>
        <extent unit="page">
            <start>347</start>
            <end>349</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Extracting Syntactic Trees from Transformer Encoder Self-Attentions
%A Mareček, David
%A Rosa, Rudolf
%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 marecek-rosa-2018-extracting
%X This is a work in progress about extracting the sentence tree structures from the encoder’s self-attention weights, when translating into another language using the Transformer neural network architecture. We visualize the structures and discuss their characteristics with respect to the existing syntactic theories and annotations.
%R 10.18653/v1/W18-5444
%U https://aclanthology.org/W18-5444
%U https://doi.org/10.18653/v1/W18-5444
%P 347-349

Markdown (Informal)

[Extracting Syntactic Trees from Transformer Encoder Self-Attentions](https://aclanthology.org/W18-5444) (Mareček & Rosa, EMNLP 2018)

• Extracting Syntactic Trees from Transformer Encoder Self-Attentions (Mareček & Rosa, EMNLP 2018)

ACL

• David Mareček and Rudolf Rosa. 2018. Extracting Syntactic Trees from Transformer Encoder Self-Attentions. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 347–349, Brussels, Belgium. Association for Computational Linguistics.